Clarity-2021 challenges: Machine learning challenges for advancing hearing aid processing
In recent years, rapid advances in speech technology have been made possible by machine
learning challenges such as CHiME, REVERB, Blizzard, and Hurricane. In the Clarity …
learning challenges such as CHiME, REVERB, Blizzard, and Hurricane. In the Clarity …
A survey of code-switched speech and language processing
Code-switching, the alternation of languages within a conversation or utterance, is a
common communicative phenomenon that occurs in multilingual communities across the …
common communicative phenomenon that occurs in multilingual communities across the …
Deep learning based assessment of synthetic speech naturalness
In this paper, we present a new objective prediction model for synthetic speech naturalness.
It can be used to evaluate Text-To-Speech or Voice Conversion systems and works …
It can be used to evaluate Text-To-Speech or Voice Conversion systems and works …
[PDF][PDF] Building multilingual end-to-end speech synthesisers for indian languages
Building text-to-speech (TTS) synthesisers is a difficult task, especially for low resource
languages. Language-specific modules need to be developed for system building. End-to …
languages. Language-specific modules need to be developed for system building. End-to …
[PDF][PDF] Random forests for statistical speech synthesis
AW Black, PK Muthukumar - Sixteenth Annual Conference of the …, 2015 - cs.cmu.edu
The world of statistical parametric speech synthesis continues to improve with recent
investigations of different machine learning techniques to better model spectrum, F0 and …
investigations of different machine learning techniques to better model spectrum, F0 and …
[PDF][PDF] On Building Mixed Lingual Speech Synthesis Systems.
SK Rallabandi, AW Black - Interspeech, 2017 - cs.cmu.edu
Codemixing-phenomenon where lexical items from one language are embedded in the
utterance of another-is relatively frequent in multilingual communities. However, TTS …
utterance of another-is relatively frequent in multilingual communities. However, TTS …
[PDF][PDF] The festvox indic frontend for grapheme to phoneme conversion
A Parlikar, S Sitaram, A Wilkinson… - WILDRE: Workshop on …, 2016 - cs.cmu.edu
Abstract Text-to-Speech (TTS) systems convert text into phonetic pronunciations which are
then processed by Acoustic Models. TTS frontends typically include text processing, lexical …
then processed by Acoustic Models. TTS frontends typically include text processing, lexical …
[PDF][PDF] Code-switching in Indic Speech Synthesisers.
Most Indians are inherently bilingual or multilingual owing to the diverse linguistic culture in
India. As a result, code-switching is quite common in conversational speech. The objective …
India. As a result, code-switching is quite common in conversational speech. The objective …
[PDF][PDF] How to compare TTS systems: a new subjective evaluation methodology focused on differences.
Subjective evaluation is a crucial problem in the speech processing community and
especially for the speech synthesis field, no matter what system is used. Indeed, when trying …
especially for the speech synthesis field, no matter what system is used. Indeed, when trying …
[PDF][PDF] Variational Attention Using Articulatory Priors for Generating Code Mixed Speech Using Monolingual Corpora.
SK Rallabandi, AW Black - INTERSPEECH, 2019 - cs.cmu.edu
Code Mixing-phenomenon where lexical items from one language are embedded in the
utterance of another-is relatively frequent in multilingual communities and therefore speech …
utterance of another-is relatively frequent in multilingual communities and therefore speech …