Speech Synthesis Method Research Articles

Speech synthesis method utilizing auxiliary information, medium recorded thereon the method and apparatus utilizing the method

In a method and apparatus which use actual speech as auxiliary information and synthesize speech by speech synthesis by rule, prosodic information for a phoneme sequence of each word of a word sequence obtained by an analysis of an input text is set by referring to a word dictionary, and a speech waveform sequence is obtained from the phoneme sequence of each word by referring to a speech waveform dictionary. Additional prosodic information is extracted from input actual speech, and at least one of the set prosodic information or at least one of the extracted prosodic information is selected and used to control the speech waveform sequence to create synthesized speech.

Method of speech synthesis by means of concentration and partial overlapping of waveforms

Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

遺伝的アルゴリズムに基づく音声合成のためのスペクトルパタン圧縮法

遺伝的アルゴリズムに基づく音声合成のためのスペクトルパタン圧縮法

Speech synthesizer having an acoustic element database

A speech synthesis method employs an acoustic element database that is established from phonetic sequences occurring in an interval of a speech signal in establishing the database, trajectories are determined (220) for each of the phonetic sequences containing a phonetic segment that corresponds to a particular phoneme (210). A tolerance region is then identified based on a concentration of trajectories that correspond to different phoneme sequences (230). The acoustic elements for the database (260) are formed from portions of the phonetic sequences by identifying cut points (250) in the phonetic sequences which corespond to time points along the respective trajectories proximate the tolerance region (240). In this manner, it is possible to concatenate the acoustic elements having a common junction phonemes such that perceptible discontinuities at the junction phonemes are minimized. Computationally simple and fast methods for determining the tolerance region are also disclosed.

Speech synthesis method based on application-specific synthesis units and its implementation on a 32-bit microprocessor

This paper presents a new method for text-to-speech synthesis with application-specific synthesis units. Since in text-to-speech systems, synthesis units are generally designed to cover all possible phoneme strings, such units are inefficient for a specific vocabulary. In the proposed method, synthesis units are selected from a speech database in order minimize the expected distortion of a given vocabulary. This method approximately halves the required amount of memory compared with synthetic units based on a conventional method. Moreover, with the proposed method, synthetic units can be generated according to the required memory. The performance of the speech synthesis was evaluated by making a trial system with a 32-bit microprocessor. Experimental results show that synthetic speech of sufficiently high quality can be obtained with only a few hundred kilobytes of memory and about 1.5 MIPS of computational power.

Speech synthesis apparatus and method for synthesizing speech from a character series comprising a text and pitch information

A speech synthesis method and apparatus for synthesizing speech from a character series comprising a text and pitch information. The apparatus includes a parameter generator for generating power spectrum envelopes as parameters of a speech waveform to be synthesized representing the input text in accordance with the input character series. The apparatus also includes a pitch waveform generator for generating pitch waveforms whose period equals the pitch specified by the pitch information. The pitch waveform generator generates the pitch waveforms from the input pitch information and the power spectrum envelopes generated by the parameter generator. Also provided is a speech waveform output device for outputting the speech waveform obtained by connecting the generated pitch waveforms.

The role of speech synthesis in Requiem per una veu perduda

Requiem per una veu perduda (Requiem for a lost voice in Catalan) is a piece for mezzo-soprano with on-stage effects processing and recorded electroacoustic material. The electroacoustic material consists mainly of synthesised vocal sounds and the pitches for the mezzo-soprano part were defined based upon the functioning of the speech synthesis methods used. This paper outlines the basics of one of the speech synthesis methods used to compose the piece and introduces the scheme for the definition of the pitch material for the singing. The relationship between the speech synthesis methods and the pitch material establishes the structural foundations of the piece.

Method of speech representation and synthesis using a set of high level constrained parameters

A speech synthesizing method which uses glottal modelling to determine and transform ten or fewer high level parameters into thirty-nine low level parameters using mapping relations. These parameters are inputted to a speech synthesizer to enable speech to be synthesized more simply than with prior art systems that required 50 to 60 parameters to be inputted to represent any particular speech.

Text-to-speech synthesis by concatenation using or modifying clustered phoneme waveforms on basis of cluster parameter centroids

In a waveform compilation (waveform concatenation or synthesis-by-rule) type speech synthesis method and speech synthesizer, phoneme waveform segments in natural speech waveforms are clustered, and one of the phoneme waveform segments having a parameter nearest the centroid of LPC parameters of all the phoneme waveforms in each cluster is selected and stored as a representative phoneme waveform in a waveform information memory. When synthesizing a speech waveform, representative phoneme waveforms of the same phonemes, whose context is most similar to that of each phoneme of a phoneme string of the speech to be synthesized, are selectively read out of the waveform information memory and thus read-out representative phoneme waveforms are sequentially concatenated for output as a continuous synthesized speech waveform.

Speech synthesis system and method utilizing phoneme information and rhythm information

To synthesize speech, which is clear and high in naturalness, in a Japanese-language speech synthesis system by improving not only phoneme information but also rhythm information. In the Japanese-language, the independent word speech and the adjunct word speech are remarkably different in speech characteristic. The difference in speech characteristics between them is clearly observed, particularly in rhythmical elements such as the intensity, speech, and pitch of speech. From this fact, there is provided a new rule synthesis method which uses as a speech synthesis unit an adjunct word chain unit comprising a chain of one or more adjunct words and which is capable of synthesizing speech whose naturalness is high. The portion other than the adjunct word portion, i.e., the independent word portion, is constituted in a CV/VC unit.

Automatic creation of CV templates for formant type speech synthesis based on HMM-based segmentation and syllable boundary detection

A formant type speech synthesis method has an enormous advantage in that it allows one to generate speech with various voice quality variations and talker individualities. But it has suffered from unnatural speech quality, not because of theoretical limitations but because of an incomplete set of rules for the synthesis. Any insufficient approximation to the acoustics causes degradation of the perceived quality of synthetic speech. A novel formant type speech synthesizer in Japanese based on concatenation of CV (consonant-vowel) formant-source templates obtained from natural utterances has been investigated, in which multiple sets of formant and voice source parameter values are used for each of the CV syllables. This paper describes an automatic method to create the CV formant-source templates from speech corpus. The ARX (autoregressive with exogenous input) analysis method is first used to automatically extract formant and voice source parameters and then an HMM based segmentation is performed to locate the CV segments. The segments are further analyzed to detect a starting point of the syllable. A distance measure is used to decide the number of templates needed for each of the syllables. The method is proved to be useful in creating CV templates by experiments performed on 503 Japanese sentences.

Digital waveguide speech synthesis system and method

A speech synthesizer uses a digital waveguide network to simulate operation of the human pharynx on acoustic signals. One end of the digital waveguide network is connected to a glottal signal source, and another end has a signal filter simulating operation of the acoustic interface at a person's lips. The digital waveguide network has sets of waveguide sections connected in series by junctions, each waveguide section including two digital delay lines running parallel to each other for propagating signals in opposite directions. Each waveguide junction has associated reflection and propagation coefficients. A parameter library that stores sets of glottal source and waveguide junction control parameters for generating corresponding sets of predefined speech signals. The waveguide junction control parameters cause the digital waveguide network to simulate operation of an acoustic tube with a shape corresponding to that of a human pharynx while producing predefined speech sounds. An articulation controller operates the glottal signal source and the digital waveguide network using a sequence of selected sets of said control parameters, thereby causing the synthesizer to generate a specified sequence of speech signals. In a preferred embodiment, the digital waveguide network has three interconnected network branches for simulating operation of the lower pharynx, the oropharynx and the nasopharynx. To generate speech signals corresponding to fricative consonants, the speech synthesizer has noise signal injectors positioned at various points along the digital waveguide network.

Automatic detection of accentual phrase boundaries using prosodic features and phoneme boundaries

There are two approaches for constructing an appropriate fundamental frequency (F0) control method for speech synthesis: statistical and rule-based. The statistical approach has the advantage of automatic training, but it requires a large corpora of speech that is annotated with prosodic boundaries. Recently, a method is proposed for high-accuracy detection of these boundaries [Ostendorf and Ross (1996)], given a set of prosodic boundary candidates in which almost all the correct boundaries are included. This paper proposes a detection method to generate these boundary candidates, specifically for accentual phrases which represent one of the smallest prosodic units. The detection algorithm uses local maximums and minimums of the F0 contour and low-energy regions of the speech waveform for finding candidate regions that correspond to accentual phrases and pauses in speech. The candidate phrase boundaries are then aligned to the nearest phoneme boundaries, which are detected automatically using forced alignment with a speaker-independent speech recognition system given a phoneme transcription. This method was applied to 250 read Japanese sentences. High-detection accuracy (97%) was obtained, with almost all the missed detections having valid candidates within ±3 phonemes. The insertion error rate was less than double the number of correct boundaries.

Speech synthesis by rule based on VCV waveform synthesis units

In recent years, several systematic speech synthesis methods in Japanese, that are based on the pitch synchronous waveform superposition method (PSOLA), have been proposed. Generally, the phonemic or the syllabic unit is used as the synthesis unit in these methods. Since these methods require the phonemic concatenation in the phoneme boundary position, the superposition of noise becomes a common problem. To solve the noise problem, a method is proposed based on VCV synthesis units. VCV synthesis units are concatenated in the vowel steady section. To improve the VCV method which does not consider using the unvoiced vowel originally, unvoiced vowels as the exceptional segments are regarded, and included the segments in the waveform database. When the VCV unit is divided into more primitive parts, it is useful to take the spectrum distortion into consideration when choosing segments. The method has been evaluated with 50 synthesized voices, and it was found that there is a correlation between evaluated score and spectrum distortions.

Method and apparatus for speech analysis and synthesis by sampling a power spectrum of input speech

A method for speech analysis and synthesis for obtaining synthesized speech of a high quality includes the steps of determining a short-period power spectrum by performing an FFT operation on a speech wave, sampling the spectrum at the positions corresponding to the multiples of a basic frequency, applying a cosine polynomial model to the thus obtained sample points to determine the spectrum envelope thereat, then calculating the mel cepstrum coefficients from the spectrum envelope, and effecting speech synthesis, utilizing the mel cepstrum coefficients as the filter coefficients in a synthesizing (logarithmic mel spectrum approximation) filter.

Method and apparatus for speech synthesis based on prosodic analysis

First Page

System and method for speech synthesis employing improved formant composition

A method, system and process to improve the formant composition in a speech synthesis system so that the formants are more intelligible. The system employs a process in the memory of a processor to change the starting and ending frequency of phonemes from the frequency of the independent phonemes. The process examines preceding and succeeding ending phoneme frequency values to detect similar phoneme frequency values. If a dissimilar value is detected, then the invention provides for exchange of the formants to render the resulting speech more intelligible.

Analysis of quality factors in synthetic speech produced by rules

This paper investigates how various factors affect the quality of synthetic speech produced by rules. Using rules to synthesize speech will be an important technique for providing various telecommunication services in future intelligent networks. The quality of synthetic speech is generally measured by subjectively evaluating the speech from the viewpoint of intelligibility, or by comparing it with the quality of other types of synthetic speech. However, the development of a practical speech synthesis method for use in telecommunication networks requires an overall quality evaluation, including intelligibility and naturalness. The quality should be compared with that of natural telephone speech. To establish an overall quality evaluation method, the effects of several factors on the overall quality (expressed by MOS) of speech synthesized by several Japanese text-to-speech systems are quantitatively compared with the effects of using additive speech-correlated white noise as a natural speech material. Experimental results show that such factors as subject, listening experience, average pitch frequency, and text affect synthetic speech more than natural speech. Quality evaluation characteristics due to these factors are discussed and an overall quality evaluation method for synthetic speech is proposed.

FRACTAL MODELING OF SPEECH SIGNALS

In this paper, we present a method for speech signal analysis and synthesis based on IFS theory. We consider a speech signal as the graph of a continuous function whose irregularity, measured in terms of its local Hölder exponents, is arbitrary. We extract a few remarkable points in the signal and perform a fractal interpolation between them using a classical technique based on IFS theory. We thus obtain a functional representation of the speech signal, which is well adapted to various applications, as for instance voice interpolation.

Speech synthesis apparatus and method

A language processing unit (201) identifies a word by performing language analysis on a text supplied from a text holding unit (201). A synthesis selection unit (209) selects speech synthesis processing performed by a rule-based synthesis unit (204) or speech synthesis processing performed by a prerecorded-speech-based synthesis unit (206) for a word of interest extracted from the language analysis result. The selected rule-based synthesis unit or prerecorded-speech-based synthesis unit executes speech synthesis processing for the word of interest.