A zero-resourced indigenous language phones occurrence and durations analysis for an automatic speech recognition system
This research illustrates phone occurrence analysis for an automatic speech recognition
(ASR) model of 'Adi.''Adi'is a low-resourced endangered tribal language of Arunachal …
(ASR) model of 'Adi.''Adi'is a low-resourced endangered tribal language of Arunachal …
Hierarchical softmax for end-to-end low-resource multilingual speech recognition
Low-resource speech recognition has been long-suffering from insufficient training data. In
this paper, we propose an approach that leverages neighboring languages to improve low …
this paper, we propose an approach that leverages neighboring languages to improve low …
Towards Matching Phones and Speech Representations
Learning phone types from phone instances has been a long-standing problem, while still
being open. In this work, we revisit this problem in the context of self-supervised learning …
being open. In this work, we revisit this problem in the context of self-supervised learning …
Unsupervised Forced Alignment on Syllable and Phoneme with Universal Phonetics Transcriptions
L Sun - 2023 IEEE International Conference on Signal …, 2023 - ieeexplore.ieee.org
Forced alignment inputs the sound recordings and transcription texts, then outputs the
temporal boundaries for each speech unit. Instead of the special phonemes belong to …
temporal boundaries for each speech unit. Instead of the special phonemes belong to …
Phoneme-to-Audio Forced Alignment with Basic Syllable Types and Broad Phonetic Classes
L Sun - 2023 6th International Conference on Information …, 2023 - ieeexplore.ieee.org
In this work, an unsupervised system of forced alignment is proposed and can be
generalized to any language without the need for manually-aligned training data …
generalized to any language without the need for manually-aligned training data …
A Computational Account of Selected Patterns of Linguistic Variation and Change
J Zhu - 2022 - deepblue.lib.umich.edu
Language variation and change are ubiquitous, and one aim of linguistic research is to
understand synchronic variation and how it contributes to change over time. This …
understand synchronic variation and how it contributes to change over time. This …
Automatic Phonemic Transcription Using Feature Fusing of Articulatory Attribute and Syllable Type
L Sun - 2022 5th International Conference on Information …, 2022 - ieeexplore.ieee.org
In this paper, we aim to improve the accuracy of automatic phonemic transcription which
takes as inputs frame-level feature sequences and outputs phoneme sequences. The more …
takes as inputs frame-level feature sequences and outputs phoneme sequences. The more …