JPH02153397A - Voice recording device - Google Patents

Voice recording device

Info

Publication number
JPH02153397A
JPH02153397A JP63308137A JP30813788A JPH02153397A JP H02153397 A JPH02153397 A JP H02153397A JP 63308137 A JP63308137 A JP 63308137A JP 30813788 A JP30813788 A JP 30813788A JP H02153397 A JPH02153397 A JP H02153397A
Authority
JP
Japan
Prior art keywords
voice
recording
standard
standard sound
feature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP63308137A
Other languages
Japanese (ja)
Other versions
JP2734028B2 (en
Inventor
Kazuhiko Iwata
和彦 岩田
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP63308137A priority Critical patent/JP2734028B2/en
Publication of JPH02153397A publication Critical patent/JPH02153397A/en
Application granted granted Critical
Publication of JP2734028B2 publication Critical patent/JP2734028B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Landscapes

  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Signal Processing Not Specific To The Method Of Recording And Reproducing (AREA)

Abstract

PURPOSE:To record a voice of accurate pitch frequency by calculating the distance between the feature quantity of a sounded voice and the feature quantity of a standard voice and recording the sounded voice only when the distance between the two feature quantities is sufficiently short. CONSTITUTION:The standard voice (b) of necessary accurate pitch frequency is generated by a standard voice generating circuit 3 and a voicing person hears it and utters a voice which is considered to have the same pitch. The uttered voice (d) is inputted to a voice feature quantity calculating circuit 6 through a microphone 5 and information (e) on the feature quantity of the voice is outputted to a recording permission signal generating circuit 7. At this time, similar information (c) on the standard voice (e) is calculated. The permission signal generating circuit 7 compares those pieces of information (e) and (c) to find the distance between the two feature quantities and a sound recording circuit 9 records the uttered voice (d) only when the distance between the feature quantities is smaller than a predetermined threshold value. Thus, the voice of accurate pitch frequency can be recorded.

Description

【発明の詳細な説明】 〔産業上の利用分野〕 本発明は音声合成等に用いる音声データを収録するため
の音声収録装置に関する。
DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a voice recording device for recording voice data used for voice synthesis and the like.

〔従来の技術〕[Conventional technology]

音声合成方式の一つとして、次のようなものが知られて
いる(日本音響学会発行の音声研究会資料記載のrev
、vc波形のピンチ周期的補間による任意語合成方式」
、資料番号582−06 (19B2−4))。
The following is known as one of the speech synthesis methods (rev.
, Arbitrary word synthesis method using pinch periodic interpolation of VC waveforms.”
, document number 582-06 (19B2-4)).

先ず、ピッチ周波数の異なる単音節等を単位音声として
複数種類予め録音しておく。この録音は単位音声を人が
発声することにより行われる。次に、合成する単語や文
書のイントネーションパターンに従って、録音されてい
る単位音声の中から単語等に最も近いピッチ周波数を有
する単位音声を選択し、これらを編集することにより音
声を合成していた。
First, a plurality of types of single syllables and the like having different pitch frequencies are recorded in advance as unit sounds. This recording is performed by a person uttering a unit voice. Next, according to the intonation pattern of the word or document to be synthesized, a unit voice having a pitch frequency closest to that of the word is selected from among the recorded unit voices, and these are edited to synthesize the voice.

ここで、予め発声録音されている単位音声のピッチ周波
数を変更せずに最も近いピッチ周波数を有する単位音声
を選択し、これらの単位音声を接続して単語や文章のイ
ントネーションを合成する方式を採っている理由は、予
め発声録音されている単位音声のピッチ周波数を変更す
ると合成音声の音質が著しく劣化するからである。
Here, a method is adopted in which the unit voice with the closest pitch frequency is selected without changing the pitch frequency of the unit voice recorded in advance, and these unit voices are connected to synthesize the intonation of a word or sentence. The reason for this is that if the pitch frequency of a unit voice that has been recorded in advance is changed, the sound quality of the synthesized voice will be significantly degraded.

従って、このような音声合成方式に用いる単位音声とし
ては、必要なピッチ周波数で正確に発声されたものを収
録しておかねばならない。
Therefore, unit speech used in such a speech synthesis method must be recorded accurately uttered at the required pitch frequency.

従来、このような音声合成方式で用いられる単位音声の
収録に4予め定められたピッチ周波数を有する標準音を
発声者に聴取させ、その標準音にできるだけ近いと発声
者が感するピッチ周波数で発声者に発声させ、それを録
音するという装置が用いられていた(特公昭54−52
682号「音声収録装置」)。
Conventionally, to record unit sounds used in such speech synthesis methods, the speaker is made to listen to a standard tone with a predetermined pitch frequency, and the speaker is uttered at a pitch frequency that the speaker feels is as close as possible to the standard tone. A device was used to make the person speak and record it.
No. 682 "Audio Recording Device").

〔発明が解決しようとする課題〕 上述した従来の音声収録装置は、発声者に標準音を聴取
させ、発声者の聴覚でピンチ周波数の遠近を判断させる
構造であったため、以下の欠点がある。
[Problems to be Solved by the Invention] The conventional audio recording device described above has the following drawbacks because it has a structure in which the speaker listens to a standard tone and uses the speaker's hearing to determine the distance of the pinch frequency.

(イ)発声者が必要なピッチ周波数を正確に発声するこ
とは困難である。
(b) It is difficult for the speaker to accurately vocalize the required pitch frequency.

(ロ)発声者がどの程度標準音に対応して正確に発声し
たかを発声者自身がその場で知ることができないため、
音声収録後、合成時に発声された音声のピッチ周波数を
修正しなくてはならない。この結果、合成音声の品質劣
化は避けることができなかった。また甚だしい場合には
、再度収録を行うといったことが必要であった。
(b) Since the speaker cannot know on the spot how accurately the speaker corresponds to the standard sounds,
After recording the audio, the pitch frequency of the uttered audio must be corrected during synthesis. As a result, deterioration in the quality of synthesized speech was unavoidable. In extreme cases, it would be necessary to record again.

本発明の目的は、上記課題を解決し、音声合成等に用い
る音声データの収録において必要とされる正確なピンチ
周波数を有する音声を収録することを可能にする音声収
録装置を提供することにある。
SUMMARY OF THE INVENTION An object of the present invention is to provide an audio recording device that solves the above problems and makes it possible to record audio having an accurate pinch frequency required for recording audio data used in audio synthesis, etc. .

〔課題を解決するための手段〕[Means to solve the problem]

本発明は、予め定められたピンチ周波数を有する標準音
を発声者に聴取させ、この標準音に近いピッチ周波数の
音声を発声させ、この音声を収録する音声収録装置であ
って、 入力されたピッチ周波数を有する前記標準音を生成する
ための標準音生成手段と、 この標準音生成手段で生成された標準音の特徴量を算出
する標準音特徴量算出手段と、前記発声音声の特徴量を
算出する音声時(tajt算出手段と、 この音声特徴量算出手段により算出された音声の特徴量
と前記標準音特徴量算出手段により算出された標準音の
特徴量との間の距離を算出し、この距離が所定の値より
も小さい場合に前記発声音声の収録許可信号を発生する
収録許可信号発生手段と、 前記収録許可信号に基づいて前記音声を収録する録音手
段とを備えていることを特徴とする。
The present invention is an audio recording device that allows a speaker to listen to a standard tone having a predetermined pinch frequency, utters a voice with a pitch frequency close to the standard tone, and records this voice, the device having the following characteristics: a standard sound generating means for generating the standard sound having a frequency; a standard sound feature calculating means for calculating the feature of the standard sound generated by the standard sound generating means; and a standard sound feature calculating means for calculating the feature of the uttered sound. Calculate the distance between the voice feature calculated by the voice feature amount calculation means and the standard sound feature amount calculated by the standard sound feature amount calculation means, It is characterized by comprising a recording permission signal generating means for generating a recording permission signal of the uttered voice when the distance is smaller than a predetermined value, and a recording means for recording the voice based on the recording permission signal. do.

〔作用〕[Effect]

本発明では、まず必要とされる正確なピッチ周波数を有
する標準音を標準音生成手段により生成して発声者に聴
取させ、同じ高さと思われる音声を発声者に発声させる
。発声された音声を音声時fXkfft算出手段により
分析して音声の持つ特徴量を算出する。算出する特徴量
としては、ピンチ周波数が考えられる。このとき、前記
標準音についても標準音特徴量算出手段を用いて同様の
特徴量を算出する。次に、収録許可信号発生手段により
、前記音声の特徴量と標準音の特徴量とを比較し、2つ
の特徴量の距離を求める。例えば、特徴量としてピンチ
周波数を用いた場合を考えると、音声と標準音の各々の
平均ピッチ周波数を算出し、その差を距離とすることが
できる。このようにして得られた距離を予め定めておい
た闇値と比較し、前記距離が前記闇値よりも小さい場合
にのみ発声された音声を録音手段を用いて収録する。距
離が闇値よりも大きい場合は、距離が闇値よりも小さい
値を取るまで、発声をやり直す。
In the present invention, first, a standard sound having the required accurate pitch frequency is generated by the standard sound generating means, the speaker is made to listen to it, and the speaker is made to produce a sound that is thought to have the same pitch. The uttered voice is analyzed by the voice fXkfft calculation means to calculate the feature amount of the voice. A pinch frequency can be considered as the feature quantity to be calculated. At this time, similar feature amounts are calculated for the standard sound using the standard sound feature amount calculation means. Next, the recording permission signal generating means compares the feature amount of the voice with the feature amount of the standard sound, and calculates the distance between the two feature amounts. For example, considering the case where the pinch frequency is used as the feature amount, it is possible to calculate the average pitch frequency of each of the voice and the standard tone, and use the difference between them as the distance. The distance thus obtained is compared with a predetermined darkness value, and only when the distance is smaller than the darkness value, the uttered voice is recorded using a recording means. If the distance is greater than the darkness value, the utterance is repeated until the distance becomes smaller than the darkness value.

以上のように、発声された音声の特徴量と標準音の特徴
量との距離を算出し、2つの特徴量の距離が十分に近い
場合にのみ、発声された音声を収録することにより、標
準音を呈示していただけの従来方法に比べ、より正確な
ピッチ周波数を有する音声を確実に収録することが可能
となる。
As described above, by calculating the distance between the features of the uttered voice and the features of the standard sound, and recording the uttered voice only when the distance between the two features is sufficiently close, the standard Compared to conventional methods that only present sounds, it is possible to reliably record sounds with more accurate pitch frequencies.

なお、前記距離を求める際に用いる特@量としてはピッ
チ周波数のほか、パワー(音の強さ)など併せて用いる
ことも可能であり、これらを総合した距離を算出するこ
とは、さらに正確なピッチを有する音声を収録するのに
有効である。
In addition to the pitch frequency, it is also possible to use power (sound intensity) as the special quantity used to calculate the distance, and calculating the distance by combining these is more accurate. This is effective for recording pitched voices.

〔実施例〕〔Example〕

本発明の実施例について図面を参照して説明する。 Embodiments of the present invention will be described with reference to the drawings.

第1図は本発明の一実施例に係る音声収録装置である。FIG. 1 shows an audio recording device according to an embodiment of the present invention.

音声収録装置1は、ピッチ周波数入力端子2を有する標
準音生成回路3(標準音生成手段)と、この標準音生成
回路3の出力側に接続された標準音特徴量算出回路4 
(標準音特徴量算出手段)と、マイクロホン5に接続さ
れた音声特@、量算出回路6(音声特徴量算出手段)と
、標準音特@、量算出回路4と音声性微量算出回路の出
力側に接続された収録許可信号発生回路7 (収録許可
信号発生手段)と、スイッチ8を介してマイクロホン5
に接続された録音回路9(録音手段)とを備えている。
The audio recording device 1 includes a standard sound generation circuit 3 (standard sound generation means) having a pitch frequency input terminal 2, and a standard sound feature calculation circuit 4 connected to the output side of the standard sound generation circuit 3.
(standard sound feature amount calculation means), the audio characteristic @, amount calculation circuit 6 (sound feature amount calculation means) connected to the microphone 5, the standard sound characteristics @, amount calculation circuit 4, and the output of the phonetic trace amount calculation circuit Recording permission signal generation circuit 7 (recording permission signal generation means) connected to the side and microphone 5 via switch 8.
A recording circuit 9 (recording means) connected to the recording circuit 9 is provided.

標準音声生成回路3は、ピンチ周波数入力端子2から入
力したピンチ周波数aに基づいてこのピッチ周波数aを
有する音声の標準音を生成し、生成した標準音すを標準
音特徴量算出回路4及びレシーバIOに出力する機能を
有する。ここで生成される標準音は、正弦波、矩形波又
は三角波等である。この他にも標準音として合成音声を
用いることも可能である。
The standard sound generation circuit 3 generates a standard sound of the sound having the pitch frequency a based on the pinch frequency a inputted from the pinch frequency input terminal 2, and sends the generated standard sound to the standard sound feature calculation circuit 4 and the receiver. It has a function to output to IO. The standard sound generated here is a sine wave, a rectangular wave, a triangular wave, or the like. In addition to this, it is also possible to use synthesized speech as the standard sound.

標準音特徴量算出回路4は、標準音生成回路3からの標
準音すを入力し、この標準音すのピッチ周波数やパワー
等の特徴量を算出して、標準音すの特徴量を示す情報C
を収録許可信号発生回路7に出力する機能を有する。
The standard sound feature calculation circuit 4 receives the standard sound from the standard sound generation circuit 3, calculates the pitch frequency, power, etc. of the standard sound, and generates information indicating the feature of the standard sound. C
It has a function of outputting to the recording permission signal generation circuit 7.

音声性微量算出回路6は、マイクロホン5から入力した
音声dのピッチ周波数やパワー等の特徴量を算出して音
声dの特徴量を示す情報eを収録許可信号発生回路7に
出力する機能を有する。
The vocal trace amount calculation circuit 6 has a function of calculating feature quantities such as pitch frequency and power of the voice d input from the microphone 5 and outputting information e indicating the feature quantity of the voice d to the recording permission signal generation circuit 7. .

収録許可信号発生回路7は、制御線11を介してスイッ
チ8の開閉制御を行う機能を有する。具体的には、標準
音特徴量算出回路4と音声性微量算出回路6から入力し
た情報cとeに基づいて、情報Cが示す標準音の特徴量
と情fW eが示す音声の特徴量との距離、即ち類似の
度合を算出し、その値が所定の闇値より小さいと判断し
た場合に制御線11を介して制1ffll信号rをスイ
ッチ8に出力してスイッチ8を閉じる機能を有する。
The recording permission signal generation circuit 7 has a function of controlling the opening and closing of the switch 8 via the control line 11. Specifically, based on the information c and e inputted from the standard sound feature amount calculation circuit 4 and the phonetic trace amount calculation circuit 6, the standard sound feature amount indicated by the information C and the voice feature amount indicated by the information fW e are calculated. It has a function of calculating the distance, that is, the degree of similarity, and outputting a control signal r to the switch 8 via the control line 11 to close the switch 8 when the value is determined to be smaller than a predetermined darkness value.

録音回路9は、マイクロホン5から閉状態のスイッチ8
を介して入力した音声dを録音する機能を有する。この
録音回路9としてテープレコーダを用いれば、音声dを
磁気テープに録音することができる。また音声dの信号
をアナログ/ディジタル変換を用いてディジタル信号に
変換し、これをメモリや磁気ディスクに蓄える録音回路
9も可能である。
The recording circuit 9 connects the microphone 5 to the switch 8 in the closed state.
It has a function to record the voice d input through the . If a tape recorder is used as the recording circuit 9, the audio d can be recorded on a magnetic tape. It is also possible to use a recording circuit 9 that converts the audio d signal into a digital signal using analog/digital conversion and stores this in a memory or a magnetic disk.

次に、本実施例に係る音声収録装置の動作について説明
する。
Next, the operation of the audio recording device according to this embodiment will be explained.

ピンチ周波数入力端子2からピッチ周波数aを入力する
と、標準音生成回路3によってピンチ周波数aを有する
音声の標準音すが生成される。
When the pitch frequency a is input from the pinch frequency input terminal 2, the standard sound generation circuit 3 generates a standard sound of the voice having the pinch frequency a.

この標準音すは、標準音特徴量算出回路4に入力され、
標準音特徴量算出回路4は、標準音すの特徴量を示す情
報Cを収録許可信号発生回路7に出力する。また、標準
音すはレシーバ10にも出力されるから、発声者はレシ
ーバ10によってピッチ周波数aの標準音すを聴くこと
ができる。
This standard sound is input to the standard sound feature calculation circuit 4,
The standard sound feature amount calculation circuit 4 outputs information C indicating the feature amount of the standard sound to the recording permission signal generation circuit 7. Furthermore, since the standard tone is also output to the receiver 10, the speaker can listen to the standard tone of pitch frequency a through the receiver 10.

発声者は、レシーバ10から標準音すを聴取し、そのピ
ッチ周波数aと等しいと思われるピッチ周波数で音声d
を発声する。
A speaker listens to a standard tone from the receiver 10, and produces a voice d at a pitch frequency that is considered to be equal to the pitch frequency a.
utter.

発声された音声dはマイクロホン5を介して音声特fa
t算出回路6に入力され、音声特@、量算出回路6は音
声dの特filtを示す情報eを収録許可信号発生回路
7に出力する。
The uttered voice d is transmitted through the microphone 5 to the voice characteristic fa.
The signal is input to the t calculation circuit 6, and the audio characteristic @, amount calculation circuit 6 outputs information e indicating the characteristic filt of the audio d to the recording permission signal generation circuit 7.

収録許可信号発生回路7に出力した情報Cとeは、その
特徴量を比較される。収録許可信号発生回路7は、これ
らの特徴量の距離が前記闇値よりも大きいと判断した場
合にはスイッチ8を開状態にする制御信号fをスイッチ
8に出力する。従ってこの場合には、音声dは録音回路
9に録音されないため、発声者は再度正確な音声dを発
生する。
The information C and e outputted to the recording permission signal generation circuit 7 are compared in terms of their feature amounts. When the recording permission signal generating circuit 7 determines that the distance between these feature amounts is larger than the darkness value, it outputs a control signal f to the switch 8 to open the switch 8. Therefore, in this case, since the voice d is not recorded in the recording circuit 9, the speaker generates the correct voice d again.

一方、特徴量の距離が前記闇値よりも小さいと判断した
場合には、スイッチ8を閉状態にする制御信号fがスイ
ッチ8に出力され、音声dは録音回路9に入力して正確
な音声として録音される。
On the other hand, if it is determined that the distance of the feature amount is smaller than the darkness value, a control signal f that closes the switch 8 is output to the switch 8, and the audio d is input to the recording circuit 9 to produce accurate audio. recorded as.

従って、各種のピンチ周波数の音声を発声者が発声する
ことにより、正確な音声が複数種類にわたって録音回路
9に収録される。
Therefore, when the speaker utters voices with various pinch frequencies, a plurality of types of accurate voices are recorded in the recording circuit 9.

〔発明の効果〕〔Effect of the invention〕

本発明の音声収録装置は、以上説明したように構成され
ているため、以下の効果がある。
Since the audio recording device of the present invention is configured as described above, it has the following effects.

(イ)必要なピッチ周波数を持った音声を、従来方式に
比べより確実に収録することができる。
(b) It is possible to record audio with the necessary pitch frequency more reliably than with conventional methods.

(ロ)必要なピンチ周波数を持った音声を収録する作業
を、大幅に軽減することができる。
(b) The work of recording audio with the necessary pinch frequency can be significantly reduced.

【図面の簡単な説明】[Brief explanation of the drawing]

第1図は本発明の一実施例に係る音声収録装置を示すブ
ロック図である。 工・・・・・音声収録装置 3・・・・・標準音生成回路(標準音生成年段) ・・・・・標準音特徴量算出回路(標準音特徴量算出手
段) ・・・・・音声特徴量算出回路(音声特徴量算出手段) ・・・・・収録許可信号発生回路(収録許可信号発生手
段) ・・・・・録音回路(録音手段)
FIG. 1 is a block diagram showing an audio recording device according to an embodiment of the present invention. Engineering: Audio recording device 3: Standard sound generation circuit (standard sound generation stage): Standard sound feature calculation circuit (standard sound feature calculation means): Audio feature calculation circuit (audio feature calculation means) Recording permission signal generation circuit (recording permission signal generation means) Recording circuit (recording means)

Claims (1)

【特許請求の範囲】[Claims] (1)予め定められたピッチ周波数を有する標準音を発
声者に聴取させ、この標準音に近いピッチ周波数の音声
を発声させ、この音声を収録する音声収録装置であって
、 入力されたピッチ周波数を有する前記標準音を生成する
ための標準音生成手段と、 この標準音生成手段で生成された標準音の特徴量を算出
する標準音特徴量算出手段と、 前記発声音声の特徴量を算出する音声特徴量算出手段と
、 この音声特徴量算出手段により算出された音声の特徴量
と前記標準音特徴量算出手段により算出された標準音の
特徴量との間の距離を算出し、この距離が所定の値より
も小さい場合に前記発声音声の収録許可信号を発生する
収録許可信号発生手段と、 前記収録許可信号に基づいて前記音声を収録する録音手
段とを備えていることを特徴とする音声収録装置。
(1) An audio recording device that allows a speaker to listen to a standard tone having a predetermined pitch frequency, utters a voice with a pitch frequency close to this standard tone, and records this voice, the device having the input pitch frequency a standard sound generating means for generating the standard sound having the standard sound; a standard sound feature calculating means for calculating the feature of the standard sound generated by the standard sound generating means; and a standard sound feature calculating means for calculating the feature of the uttered sound. A voice feature amount calculation means calculates a distance between the voice feature amount calculated by the voice feature amount calculation means and the standard sound feature amount calculated by the standard sound feature amount calculation means, A sound characterized by comprising: recording permission signal generating means for generating a recording permission signal for the uttered voice when the value is smaller than a predetermined value; and recording means for recording the voice based on the recording permission signal. Recording device.
JP63308137A 1988-12-06 1988-12-06 Audio recording device Expired - Lifetime JP2734028B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP63308137A JP2734028B2 (en) 1988-12-06 1988-12-06 Audio recording device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP63308137A JP2734028B2 (en) 1988-12-06 1988-12-06 Audio recording device

Publications (2)

Publication Number Publication Date
JPH02153397A true JPH02153397A (en) 1990-06-13
JP2734028B2 JP2734028B2 (en) 1998-03-30

Family

ID=17977336

Family Applications (1)

Application Number Title Priority Date Filing Date
JP63308137A Expired - Lifetime JP2734028B2 (en) 1988-12-06 1988-12-06 Audio recording device

Country Status (1)

Country Link
JP (1) JP2734028B2 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06195093A (en) * 1992-10-01 1994-07-15 Nec Corp Automatic tone quality evaluating device
JPH06236198A (en) * 1993-02-09 1994-08-23 Nec Corp Tone quality subjective evaluation prediction system
JP2002132287A (en) * 2000-10-20 2002-05-09 Canon Inc Speech recording method and speech recorder as well as memory medium
JP2007256349A (en) * 2006-03-20 2007-10-04 Oki Electric Ind Co Ltd Voice data recording system and voice data recording method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06195093A (en) * 1992-10-01 1994-07-15 Nec Corp Automatic tone quality evaluating device
JPH06236198A (en) * 1993-02-09 1994-08-23 Nec Corp Tone quality subjective evaluation prediction system
JP2002132287A (en) * 2000-10-20 2002-05-09 Canon Inc Speech recording method and speech recorder as well as memory medium
JP2007256349A (en) * 2006-03-20 2007-10-04 Oki Electric Ind Co Ltd Voice data recording system and voice data recording method

Also Published As

Publication number Publication date
JP2734028B2 (en) 1998-03-30

Similar Documents

Publication Publication Date Title
US5704007A (en) Utilization of multiple voice sources in a speech synthesizer
US5828994A (en) Non-uniform time scale modification of recorded audio
US5930755A (en) Utilization of a recorded sound sample as a voice source in a speech synthesizer
HU176776B (en) Method and apparatus for synthetizing speech
JP2005070430A (en) Speech output device and method
JP2734028B2 (en) Audio recording device
JP5175422B2 (en) Method for controlling time width in speech synthesis
JPH05307395A (en) Voice synthesizer
JPH0549998B2 (en)
US7130799B1 (en) Speech synthesis method
JP2005523478A (en) How to synthesize speech
US20050171777A1 (en) Generation of synthetic speech
JP2001154684A (en) Speech speed converter
JPH08248993A (en) Controlling method of phoneme time length
JPH0462600B2 (en)
JPH02293900A (en) Voice synthesizer
JP3022270B2 (en) Formant sound source parameter generator
JP2840234B2 (en) Rule-based speech synthesizer
JPH11161297A (en) Method and device for voice synthesizer
JPH02153398A (en) Voice recording device
JP3133347B2 (en) Prosody control device
JPH05173587A (en) Speech synthesizer
KR940011871B1 (en) Voice generating device
JPH05257494A (en) Voice rule synthesizing system
JPS63210898A (en) Voice synthesizer