This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This paper also contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years. Advantages and disadvantages of statistical parametric synthesis are highlighted as well as identifying where we expect the key developments to appear in the immediate future.

https://www.sp.nitech.ac.jp/~bonanza/Paper/EMIME/zen_specom.pdf

Statistical Parametric Speech Synthesis

This paper explores two related factors which influence variation in duration, prosodic structure and redundancy in spontaneous speech. We argue that the constraint of producing robust communication while efficiently expending articulatory effort leads to an inverse relationship between language redundancy and duration. The inverse relationship improves communication robustness by spreading information more evenly across the speech signal, yielding a smoother signal redundancy profile. We argue that prosodic prominence is a linguistic means of achieving smooth signal redundancy. Prosodic prominence increases syllable duration and coincides to a large extent with unpredictable sections of speech, and thus leads to a smoother signal redundancy. The results of linear regressions carried out between measures of redundancy, syllable duration and prosodic structure in a large corpus of spontaneous speech confirm: (1) an inverse relationship between language redundancy and duration, and (2) a strong relationship between prosodic prominence and duration. The fact that a large proportion of the variance predicted by language redundancy and prosodic prominence is nonunique suggests that, in English, prosodic prominence structure is the means with which constraints caused by a robust signal requirement are expressed in spontaneous speech.

The smooth signal redundancy hypothesis: a functional explanation for relationships between redundancy, prosodic prominence, and duration in spontaneous speech.

This paper gives a general overview of hidden Markov model (HMM)-based speech synthesis, which has recently been demonstrated to be very effective in synthesizing speech. The main advantage of this approach is its flexibility in changing speaker identities, emotions, and speaking styles. This paper also discusses the relation between the HMM-based approach and the more conventional unit-selection approach that has dominated over the last decades. Finally, advanced techniques for future developments are described.

/pdf/speech-synthesis-based-on-hidden-markov-models-45y6v1rk5u.pdf

Speech Synthesis Based on Hidden Markov Models

The Discovery of Spoken Language, Peter W. Jusczyk (Ed.). MIT Press (1997), ISBN 0 262 10058 4

A short-term longitudinal study was carried out on a group of 67 preschool children. At three points in time over a 12-month period, the children were given tests measuring their syllable, rime, and phoneme awareness, speech and language skills, and letter knowledge. In general, children's rime skills developed earlier than their phoneme skills. Structural equation models showed that articulatory skills and syllable and rime awareness predicted later phoneme awareness.

/pdf/the-development-of-phonological-awareness-in-preschool-5ftul9388g.pdf

The development of phonological awareness in preschool children.

The Blizzard Challenge 2008 was the fourth annual Blizzard Challenge. This year, participants were asked to build two voices from a UK English corpus and one voice from a Man- darin Chinese corpus. This is the first time that a language other than English has been included and also the first time that a large UK English corpus has been available. In addi- tion, the English corpus contained somewhat more expressive speech than that found in corpora used in previous Blizzard Challenges. To assist participants with limited resources or limited ex- perience in UK-accented English or Mandarin, unaligned la- bels were provided for both corpora and for the test sentences. Participants could use the provided labels or create their own. An accent-specific pronunciation dictionary was also available for the English speaker. A set of test sentences was released to participants, who were given a limited time in which to synthesise them and submit the synthetic speech. An online listening test was con- ducted, to evaluate naturalness, intelligibility and degree of similarity to the original speaker Index Terms: Blizzard Challenge, speech synthesis, evalua- tion, listening test

/pdf/the-blizzard-challenge-2008-32oxbj7uqv.pdf

The Blizzard Challenge 2008

https://www.cstr.ed.ac.uk/downloads/publications/2012/Cooke_SPCOM13.pdf

Evaluating the intelligibility benefit of speech modifications in known noise conditions

Blizzard 2007 is the third Blizzard Challenge, in which participants build voices from a common dataset. A large listening test is conducted which allows comparison of systems in terms of naturalness and intelligibility. New sections were added to the listening test for 2007 to test the perceived similarity of the speaker’s identity between natural and synthetic speech. In this paper, we present the results of the listening test and the subsequent statistical analysis Index Terms: Blizzard Challenge, speech synthesis, evaluation, listening test

/pdf/statistical-analysis-of-the-blizzard-challenge-2007-391n6kp3e4.pdf

Statistical analysis of the Blizzard Challenge 2007 listening test results

It has been proposed that young children may have a perceptual preference for transitional cues [Nittrouer, S. (2002). J. Acoust. Soc. Am. 112, 711–719]. According to this proposal, this preference can manifest itself either as heavier weighting of transitional cues by children than by adults, or as heavier weighting of transitional cues than of other, more static, cues by children. This study tested this hypothesis by examining adults’ and children’s cue weighting for the contrasts /saɪ/-/∫aɪ/, /de/-/be/, /ta/-/da/, and /ti/-/di/. Children were found to weight transitions more heavily than did adults for the fricative contrast /saɪ/-/∫aɪ/, and were found to weight transitional cues more heavily than nontransitional cues for the voice-onset-time contrast /ta/-/da/. However, these two patterns of cue weighting were not found to hold for the contrasts /de/-/be/ and /ti/-/di/. Consistent with several studies in the literature, results suggest that children do not always show a bias towards vowel–formant transitions, but that cue weighting can differ according to segmental context, and possibly the physical distinctiveness of available acoustic cues.

Adult–child differences in acoustic cue weighting are influenced by segmental context: Children are not always perceptually biased toward transitions

Speech output is used extensively, including in situations where correct message reception is threatened by adverse listening conditions. Recently, there has been a growing interest in algorithmic modifications that aim to increase the intelligibility of both natural and synthetic speech when presented in noise. The Hurricane Challenge is the first large-scale open evaluation of algorithms designed to enhance speech intelligibility. Eighteen systems operating on a common data set were subjected to extensive listening tests and compared to unmodified natural and text-to-speech (TTS) baselines. The best-performing systems achieved gains over unmodified natural speech of 4.4 and 5.1 dB in competing speaker and stationary noise respectively, while TTS systems made gains of 5.6 and 5.1 dB over their baseline. Surprisingly, for most conditions the largest gains were observed for noise-independent algorithms, suggesting that performance in this task can be further improved by exploiting information in the masking signal.

/pdf/intelligibility-enhancing-speech-modifications-the-hurricane-44y7iq45cg.pdf

Catherine Mayo

Papers

The Blizzard Challenge 2008

Evaluating the intelligibility benefit of speech modifications in known noise conditions

Statistical analysis of the Blizzard Challenge 2007 listening test results

Adult–child differences in acoustic cue weighting are influenced by segmental context: Children are not always perceptually biased toward transitions

Intelligibility-enhancing speech modifications: the Hurricane Challenge