Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPhoneme Level Language Models for Sequence Based Low Resource ASR
80
0
0.0
(
0
)
Added by
Siddharth Dalmia
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a new language. These approaches are particularly useful for low resource languages. In this paper, we propose a phoneme-level language model that can be used multilingually and for crosslingual adaptation to a target language. We show that our model performs almost as well as the monolingual models by using six times fewer parameters, and is capable of better adaptation to languages not seen during training in a low resource scenario. We show that these phoneme-level language models can be used to decode sequence based Connectionist Temporal Classification (CTC) acoustic model outputs to obtain comparable word error rates with Weighted Finite State Transducer (WFST) based decoding in Babel languages. We also show that these phoneme-level language models outperform WFST decoding in various low-resource conditions like adapting to a new language and domain mismatch between training and testing data.
rate research
Read More
Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for seq2seq models than their hybrid counterparts. We examine corpora of five languages from the IARPA MATERIAL program where the transcribed data is conversational telephone speech (CTS) and evaluation data is broadcast news (BN). We show that there is a sizable initial gap in such a data condition between hybrid and seq2seq models, and the hybrid model is able to further improve through the use of additional language model (LM) data. We use an additional set of untranscribed data primarily in the BN domain for semisupervised training. In semisupervised training, a seed model trained on transcribed data generates hypothesized transcripts for unlabeled domain-matched data for further training. By using a hybrid model with an expanded language model for pseudotranscription, we are able to improve our seq2seq model from an average word error rate (WER) of 66.7% across all five languages to 29.0% WER. While this puts the seq2seq model at a competitive operating point, hybrid models are still able to use additional LM data to maintain an advantage.
Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match the ground truth as equally poor, ignoring the structure of the output space. Second, it suffers from exposure bias: during training tokens are predicted given ground-truth sequences, while at test time prediction is conditioned on generated output sequences. To overcome these limitations we build upon the recent reward augmented maximum likelihood approach ie sequence-level smoothing that encourages the model to predict sentences close to the ground truth according to a given performance metric. We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach. Our experiments on two different tasks, image captioning and machine translation, show that token-level and sequence-level loss smoothing are complementary, and significantly improve results.
While speech recognition has seen a surge in interest and research over the last decade, most machine learning models for speech recognition either require large training datasets or lots of storage and memory. Combined with the prominence of English as the number one language in which audio data is available, this means most other languages currently lack good speech recognition models. The method presented in this paper shows how to create and train models for speech recognition in any language which are not only highly accurate, but also require very little storage, memory and training data when compared with traditional models. This allows training models to recognize any language and deploying them on edge devices such as mobile phones or car displays for fast real-time speech recognition.
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are attractive because of their simplicity and elegance. While it is possible to integrate traditional multi-lingual bottleneck feature extractors as front-ends, we show that end-to-end multi-lingual training of sequence models is effective on context independent models trained using Connectionist Temporal Classification (CTC) loss. We show that our model improves performance on Babel languages by over 6% absolute in terms of word/phoneme error rate when compared to mono-lingual systems built in the same setting for these languages. We also show that the trained model can be adapted cross-lingually to an unseen language using just 25% of the target data. We show that training on multiple languages is important for very low resource cross-lingual target scenarios, but not for multi-lingual testing scenarios. Here, it appears beneficial to include large well prepared datasets.
In this paper, we introduce ``Embedding Barrier, a phenomenon that limits the monolingual performance of multilingual models on low-resource languages having unique typologies. We build `BanglaBERT, a Bangla language model pretrained on 18.6 GB Internet-crawled data and benchmark on five standard NLU tasks. We discover a significant drop in the performance of the state-of-the-art multilingual model (XLM-R) from BanglaBERT and attribute this to the Embedding Barrier through comprehensive experiments. We identify that a multilingual models performance on a low-resource language is hurt when its writing script is not similar to any of the high-resource languages. To tackle the barrier, we propose a straightforward solution by transcribing languages to a common script, which can effectively improve the performance of a multilingual model for the Bangla language. As a bi-product of the standard NLU benchmarks, we introduce a new downstream dataset on natural language inference (NLI) and show that BanglaBERT outperforms previous state-of-the-art results on all tasks by up to 3.5%. We are making the BanglaBERT language model and the new Bangla NLI dataset publicly available in the hope of advancing the community. The resources can be found at url{https://github.com/csebuetnlp/banglabert}.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
