Enhancing the Intelligibility of Statistically Generated Synthetic Speech by Means of Noise-Independent Modifications

Erro, Daniel; Zorilă, Tudor-Cătălin; Stylianou, Yannis

doi:10.1109/taslp.2014.2361022

Cited by 12 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A considerable amount of research has been conducted on speaking style modification during the last years. Signal processing approaches such as cepstral modifications [4], spectral shaping [5] and glimpse proportion measure with dynamic range compression [6] were adopted to mimic the acoustic changes observed in the production of Lombard speech. Voice transformation techniques have been implemented to learn the mapping between normal speech and speech that is generated in noise [7,8].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion

Paul¹,

Shifas²,

Pantazis³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

The increased adoption of digital assistants makes textto-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the presence of noise. Past studies have investigated style conversion in TTS synthesis, yet degraded synthesized quality often leads to worse intelligibility. To overcome such limitations, we proposed a novel transfer learning approach using Tacotron and WaveRNN based TTS synthesis. The proposed speech system exploits two modification strategies: (a) Lombard speaking style data and (b) Spectral Shaping and Dynamic Range Compression (SSDRC) which has been shown to provide high intelligibility gains by redistributing the signal energy on the time-frequency domain. We refer to this extension as Lombard-SSDRC TTS system. Intelligibility enhancement as quantified by the Intelligibility in Bits (SIIB Gauss) measure shows that the proposed Lombard-SSDRC TTS system shows significant relative improvement between 110% and 130% in speech-shaped noise (SSN), and 47% to 140% in competing-speaker noise (CSN) against the state-ofthe-art TTS approach. Additional subjective evaluation shows that Lombard-SSDRC TTS successfully increases the speech intelligibility with relative improvement of 455% for SSN and 104% for CSN in median keyword correction rate compared to the baseline TTS method.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion

Paul¹,

Shifas²,

Pantazis³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, speech that is deliberately spoken clearly is easier to understand than conversational speech for both normal and hearing-impaired listeners (Picheny et al, 1985;Payton et al, 1994;Ferguson and Kewley-Port, 2002) and for non-native listeners (Bradlow and Bent, 2002;Cooke and Lecumberri, 2012). Therefore, one approach is to process conversational speech so as to mimic the effects that occur in "Lombard" speech or clearly spoken speech (Skowronski and Harris, 2006;Zorilȃ et al, 2012;Takou et al, 2013;Godoy et al, 2014;Jokinen et al, 2014;Erro et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of near-end speech enhancement under equal-loudness constraint for listeners with normal-hearing and mild-to-moderate hearing loss

Zorilă

Stylianou

Flanagan

et al. 2017

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

Four algorithms designed to enhance the intelligibility of speech when noise is added after processing were evaluated under the constraint that the speech should have the same loudness before and after processing, as determined using a loudness model. The algorithms applied spectral modifications and two of them included dynamic-range compression. On average, the methods with dynamic-range compression required the least level adjustment to equate loudness for the unprocessed and processed speech. Subjects with normal-hearing (experiment 1) and mild-to-moderate hearing loss (experiment 2) were tested using unmodified and enhanced speech presented in speech-shaped noise (SSN) and a competing speaker (CS). The results showed (a) the algorithms with dynamic-range compression yielded the largest intelligibility gains in both experiments and for both types of background; (b) the algorithms without dynamic-range compression either yielded benefit only with the SSN or yielded no consistent benefit; (c) speech reception thresholds for unprocessed speech were higher for hearing-impaired than for normal-hearing subjects, by about 2 dB for the SSN and 6 dB for the CS. It is concluded that the enhancement methods incorporating dynamic-range compression can improve intelligibility under the equal-loudness constraint for both normal-hearing and hearing-impaired subjects and for both steady and fluctuating backgrounds.

show abstract

“…In this work we choose the second strategy because it preserves the original model, thus allowing the generation of both speech and singing from the same model. The response of the filter used in this work, a deterministic one inspired by [25,26], is depicted in figure 6. Note that this filter can be applied regardless of the input voice.…”

Section: Spectral Transformationsmentioning

confidence: 99%

Bertsokantari: a TTS Based Singing Synthesis System

Blanco¹,

Hernáez

Navas

et al. 2016

Interspeech 2016

View full text Add to dashboard Cite

This paper describes the implementation of the Aholab entry for the Singing Synthesis Challenge: Fill-in the Gap. Our approach in this work makes use of an HTS based Text-to-Speech (TTS) synthesizer for Basque to generate the singing voice. The prosody related parameters provided by the TTS system for a spoken version of the score are modified to adapt them to the requirements of the music score concerning syllables duration and tone, while the spectral parameters are basically maintained. The paper describes the processing details developed to improve the quality of the output signal: the syllable timing, the generation of the intonation with vibrato and the manipulation of the model states. In this entry, the lyrics have been freely translated into Basque and the rhythm has been adapted to a Basque traditional rhythm.

show abstract

Enhancing the Intelligibility of Statistically Generated Synthetic Speech by Means of Noise-Independent Modifications

Cited by 12 publications

References 43 publications

Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion

Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion

Evaluation of near-end speech enhancement under equal-loudness constraint for listeners with normal-hearing and mild-to-moderate hearing loss

Bertsokantari: a TTS Based Singing Synthesis System

Contact Info

Product

Resources

About