[PDF][PDF] Speech synthesis evaluation—state-of-the-art assessment and suggestion for a novel research program
Speech synthesis applications have become an ubiquity, in navigation systems, digital
assistants or as screen or audio book readers. Despite their impact on the acceptability of …
assistants or as screen or audio book readers. Despite their impact on the acceptability of …
[HTML][HTML] Planning the development of text-to-speech synthesis models and datasets with dynamic deep learning
Synthesis of Text-to-speech (TTS) is a process that involves translating a natural language
text into a speech. Speech synthesisers face a major challenge when recognizing the …
text into a speech. Speech synthesisers face a major challenge when recognizing the …
Choice of voices: A large-scale evaluation of text-to-speech voice quality for long-form content
The advancement of text-to-speech (TTS) voices and a rise of commercial TTS platforms
allow people to easily experience TTS voices across a variety of technologies, applications …
allow people to easily experience TTS voices across a variety of technologies, applications …
Evaluating and personalizing user-perceived quality of text-to-speech voices for delivering mindfulness meditation with different physical embodiments
Mindfulness-based therapies have been shown to be effective in improving mental health,
and technology-based methods have the potential to expand the accessibility of these …
and technology-based methods have the potential to expand the accessibility of these …
Dynamic prosody generation for speech synthesis using linguistics-driven acoustic embedding selection
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-
human capabilities when considering isolated sentences. But something which is still …
human capabilities when considering isolated sentences. But something which is still …
Camp: a two-stage approach to modelling prosody in context
Prosody is an integral part of communication, but remains an open problem in state-of-the-
art speech synthesis. There are two major issues faced when modelling prosody:(1) prosody …
art speech synthesis. There are two major issues faced when modelling prosody:(1) prosody …
Multi-granularity annotation of instantaneous intelligibility of learners' utterances based on shadowing techniques
C Zhu, R Hakoda, D Saito, N Minematsu… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
The practical goal of pronunciation training is to acquire an intelligible enough
pronunciation, not a native-like pronunciation. In our studies [1],[2], we proposed a method …
pronunciation, not a native-like pronunciation. In our studies [1],[2], we proposed a method …
Building and designing expressive speech synthesis
We know there is something special about speech. Our voices are not just a means of
communicating. They also give a deep impression of who we are and what we might know …
communicating. They also give a deep impression of who we are and what we might know …
Measuring speech recognition with a matrix test using synthetic speech
T Nuesse, B Wiercinski, T Brand… - Trends in Hearing, 2019 - journals.sagepub.com
Speech audiometry is an essential part of audiological diagnostics and clinical
measurements. Development times of speech recognition tests are rather long, depending …
measurements. Development times of speech recognition tests are rather long, depending …
[PDF][PDF] Detection of Learners' Listening Breakdown with Oral Dictation and Its Use to Model Listening Skill Improvement Exclusively Through Shadowing.
T Kunihara, C Zhu, D Saito, N Minematsu… - …, 2022 - isca-archive.org
In language learners' speech, mispronounced words, word fragments, repairs, filled pauses,
etc are often found, and they can be detected with ASR-based CALL systems. When …
etc are often found, and they can be detected with ASR-based CALL systems. When …