Multilingual Jointly Trained Acoustic and Written Word Embeddings

• URL: http://arxiv.org/abs/2006.14007v1
• Date: Wed, 24 Jun 2020 19:16:02 GMT
• Title: Multilingual Jointly Trained Acoustic and Written Word Embeddings
• Authors: Yushi Hu, Shane Settle, Karen Livescu
• Abstract summary: We extend this idea to multiple low-resource languages. We jointly train an AWE model and an AGWE model, using phonetically transcribed data from multiple languages. The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages.
• Score: 22.63696520064212
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically grounded word embeddings (AGWEs). Such embeddings have been used to improve speech retrieval, recognition, and spoken term discovery. In this work, we extend this idea to multiple low-resource languages. We jointly train an AWE model and an AGWE model, using phonetically transcribed data from multiple languages. The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages. We also investigate distinctive features, as an alternative to phone labels, to better share cross-lingual information. We test our models on word discrimination tasks for twelve languages. When trained on eleven languages and tested on the remaining unseen language, our model outperforms traditional unsupervised approaches like dynamic time warping. After fine-tuning the pre-trained models on one hour or even ten minutes of data from a new language, performance is typically much better than training on only the target-language data. We also find that phonetic supervision improves performance over character sequences, and that distinctive feature supervision is helpful in handling unseen phones in the target language.

Related papers

• Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model [14.39119862985503]
  We aim to create a multilingual ALT system with available datasets. Inspired by architectures that have been proven effective for English ALT, we adapt these techniques to the multilingual scenario. We evaluate the performance of the multilingual model in comparison to its monolingual counterparts.
  arXiv  Detail & Related papers  (2024-06-25T15:02:32Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Learning Cross-lingual Visual Speech Representations [108.68531445641769]
  Cross-lingual self-supervised visual representation learning has been a growing research topic in the last few years. We use the recently-proposed Raw Audio-Visual Speechs (RAVEn) framework to pre-train an audio-visual model with unlabelled data. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping the amount of data fixed, monolingual models tend to reach better performance.
  arXiv  Detail & Related papers  (2023-03-14T17:05:08Z)
• Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining [2.3513645401551333]
  We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model for a new language. Our results show that continued pretraining is the most effective method to adapt a wav2vec 2.0 model for a new language. We find that if a model pretrained on a related speech variety or an unrelated language with similar phonological characteristics is available, multilingual fine-tuning using additional data from that language can have positive impact on speech recognition performance.
  arXiv  Detail & Related papers  (2023-01-18T03:57:53Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language [32.170748231414365]
  We show that training on even just a single related language gives the largest gain. We also find that adding data from unrelated languages generally doesn't hurt performance.
  arXiv  Detail & Related papers  (2021-06-24T08:37:05Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Improved acoustic word embeddings for zero-resource languages using multilingual transfer [37.78342106714364]
  We train a single supervised embedding model on labelled data from multiple well-resourced languages and apply it to unseen zero-resource languages. We consider three multilingual recurrent neural network (RNN) models: a classifier trained on the joint vocabularies of all training languages; a Siamese RNN trained to discriminate between same and different words from multiple languages; and a correspondence autoencoder (CAE) RNN trained to reconstruct word pairs. All of these models outperform state-of-the-art unsupervised models trained on the zero-resource languages themselves, giving relative improvements of more than 30% in average precision.
  arXiv  Detail & Related papers  (2020-06-02T12:28:34Z)
• That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages [72.9927937955371]
  We use the resources existing in other languages to train a multilingual automatic speech recognition model. We observe significant improvements across all languages in the multilingual setting, and stark degradation in the crosslingual setting. Our analysis uncovered that even the phones that are unique to a single language can benefit greatly from adding training data from other languages.
  arXiv  Detail & Related papers  (2020-05-16T22:28:09Z)
• Towards Zero-shot Learning for Automatic Phonemic Transcription [82.9910512414173]
  A more challenging problem is to build phonemic transcribers for languages with zero training data. Our model is able to recognize unseen phonemes in the target language without any training data. It achieves 7.7% better phoneme error rate on average over a standard multilingual model.
  arXiv  Detail & Related papers  (2020-02-26T20:38:42Z)
• Multilingual acoustic word embedding models for processing zero-resource languages [37.78342106714364]
  We train a single supervised embedding model on labelled data from multiple well-resourced languages. We then apply it to unseen zero-resource languages.
  arXiv  Detail & Related papers  (2020-02-06T05:53:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.