paper-with-me

Papers

Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition

2024-06-04 · Hao Yen, Pin-Jui Ku, Sabato Marco Siniscalchi, Chin-Hui Lee

We propose a novel language-universal approach to end-to-end automatic spoken keyword recognition (SKR) leveraging upon (i) a self-supervised pre-trained model, and (ii) a set of universal speech attributes (manner and place of articulation). Specifically, Wav2Vec2.0 is used to generate robust speech representations, followed by a linear output layer to produce attribute sequences. A non-trainable pronunciation model then maps sequences of attributes into spoken keywords in a multilingual setting. Experiments on the Multilingual Spoken Words Corpus show comparable performances to character- and phoneme-based SKR in seen languages. The inclusion of domain adversarial training (DAT) improves the proposed framework, outperforming both character- and phoneme-based SKR approaches with 13.73% and 17.22% relative word error rate (WER) reduction in seen languages, and achieves 32.14% and 19.92% WER reduction for unseen languages in zero-shot settings.

📄 PDF Abstract BibTeX arXiv:2406.02488

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Exploring Universal Speech Attributes for Speaker Verification with an Improved Cross-stitch Network

2020-10-13 · Jiajun Qi, Wu Guo, Jingjing Shi, Yafeng Chen 외

The universal speech attributes for x-vector based speaker verification (SV) are addressed in this paper. The manner and place of articulation form the fundamental speech attribute unit (SAU), and then new speech attribu…

AttributeSpeaker Verification

Zero-shot Learning for Speech Recognition with Universal Phonetic Model

2018-09-27 · Xinjian Li, Siddharth Dalmia, David R. Mortensen, Florian Metze 외

There are more than 7,000 languages in the world, but due to the lack of training sets, only a small number of them have speech recognition systems. Multilingual speech recognition provides a solution if at least some au…

speech-recognitionSpeech RecognitionZero-Shot Learning

CUPE: Contextless Universal Phoneme Encoder for Language-Agnostic Speech Processing

2025-08-21 · Abdul Rehman, Jian-Jun Zhang, Xiaosong Yang arxiv

Universal phoneme recognition typically requires analyzing long speech segments and language-specific patterns. Many speech processing tasks require pure phoneme representations free from contextual influence, which moti…

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

2018-02-23 · Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman 외

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural t…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Humanitarianspeech-recognition+1

Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations

2025-03-15 · Xue Jiang, Xiulian Peng, Yuan Zhang, Yan Lu

Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-…