A Preliminary Analysis of Automatic Word and Syllable Prominence Detection in Non-Native Speech With Text-to-Speech Prosody Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mondal, Anindita, Bharadwaj, Rangavajjala Sankara, Mallela, Jhansi, Vuppala, Anil Kumar, Yarra, Chiranjeevi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916518361563136
author Mondal, Anindita
Bharadwaj, Rangavajjala Sankara
Mallela, Jhansi
Vuppala, Anil Kumar
Yarra, Chiranjeevi
author_facet Mondal, Anindita
Bharadwaj, Rangavajjala Sankara
Mallela, Jhansi
Vuppala, Anil Kumar
Yarra, Chiranjeevi
contents Automatic detection of prominence at the word and syllable-levels is critical for building computer-assisted language learning systems. It has been shown that prosody embeddings learned by the current state-of-the-art (SOTA) text-to-speech (TTS) systems could generate word- and syllable-level prominence in the synthesized speech as natural as in native speech. To understand the effectiveness of prosody embeddings from TTS for prominence detection under nonnative context, a comparative analysis is conducted on the embeddings extracted from native and non-native speech considering the prominence-related embeddings: duration, energy, and pitch from a SOTA TTS named FastSpeech2. These embeddings are extracted under two conditions considering: 1) only text, 2) both speech and text. For the first condition, the embeddings are extracted directly from the TTS inference mode, whereas for the second condition, we propose to extract from the TTS under training mode. Experiments are conducted on native speech corpus: Tatoeba, and non-native speech corpus: ISLE. For experimentation, word-level prominence locations are manually annotated for both corpora. The highest relative improvement on word \& syllable-level prominence detection accuracies with the TTS embeddings are found to be 13.7% & 5.9% and 16.2% & 6.9% compared to those with the heuristic-based features and self-supervised Wav2Vec-2.0 representations, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08283
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Preliminary Analysis of Automatic Word and Syllable Prominence Detection in Non-Native Speech With Text-to-Speech Prosody Embeddings
Mondal, Anindita
Bharadwaj, Rangavajjala Sankara
Mallela, Jhansi
Vuppala, Anil Kumar
Yarra, Chiranjeevi
Computation and Language
Audio and Speech Processing
Automatic detection of prominence at the word and syllable-levels is critical for building computer-assisted language learning systems. It has been shown that prosody embeddings learned by the current state-of-the-art (SOTA) text-to-speech (TTS) systems could generate word- and syllable-level prominence in the synthesized speech as natural as in native speech. To understand the effectiveness of prosody embeddings from TTS for prominence detection under nonnative context, a comparative analysis is conducted on the embeddings extracted from native and non-native speech considering the prominence-related embeddings: duration, energy, and pitch from a SOTA TTS named FastSpeech2. These embeddings are extracted under two conditions considering: 1) only text, 2) both speech and text. For the first condition, the embeddings are extracted directly from the TTS inference mode, whereas for the second condition, we propose to extract from the TTS under training mode. Experiments are conducted on native speech corpus: Tatoeba, and non-native speech corpus: ISLE. For experimentation, word-level prominence locations are manually annotated for both corpora. The highest relative improvement on word \& syllable-level prominence detection accuracies with the TTS embeddings are found to be 13.7% & 5.9% and 16.2% & 6.9% compared to those with the heuristic-based features and self-supervised Wav2Vec-2.0 representations, respectively.
title A Preliminary Analysis of Automatic Word and Syllable Prominence Detection in Non-Native Speech With Text-to-Speech Prosody Embeddings
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2412.08283