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

arXiv: https://arxiv.org/abs/2406.02488 · HTML: https://mlsanity.com/paper/2406.02488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Multilingual Speech Recognition With A Single End-To-End Model](https://mlsanity.com/paper/1711.01694/) (2017)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [A neural attention model for speech command recognition](https://mlsanity.com/paper/1808.08929/) (2018)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition](https://mlsanity.com/paper/2004.08531/) (2020)
- [Speaker-Invariant Training via Adversarial Learning](https://mlsanity.com/paper/1804.00732/) (2018)
- [REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling](https://mlsanity.com/paper/2012.07353/) (2020)
- [Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes](https://mlsanity.com/paper/2306.04306/) (2023)
- [Differentiable Allophone Graphs for Language-Universal Speech Recognition](https://mlsanity.com/paper/2107.11628/) (2021)
- [Adversarial Speaker Verification](https://mlsanity.com/paper/1904.12406/) (2019)
- [Adversarial Training for Multilingual Acoustic Modeling](https://mlsanity.com/paper/1906.07093/) (2019)
- [Channel adversarial training for speaker verification and diarization](https://mlsanity.com/paper/1910.11643/) (2019)
- [Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints](https://mlsanity.com/paper/2309.08828/) (2023)

## Abstract (arXiv)

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.