Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition (2406.02488v1)

Published 4 Jun 2024 in eess.AS, cs.CL, and cs.SD

Abstract: 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.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Hao Yen (8 papers)
  2. Pin-Jui Ku (7 papers)
  3. Sabato Marco Siniscalchi (46 papers)
  4. Chin-Hui Lee (52 papers)

Summary

We haven't generated a summary for this paper yet.