Code-switching Speech Recognition Research Articles

The Evaluation of a Code-Switched Sepedi-English Automatic Speech Recognition System

Speech technology is a field that encompasses various techniques and tools used to enable machines to interact with speech, such as automatic speech recognition (ASR), spoken dialog systems, and others, allowing a device to capture spoken words through a microphone from a human speaker. End-to-end approaches such as Connectionist Temporal Classification (CTC) and attention-based methods are the most used for the development of ASR systems. However, these techniques were commonly used for research and development for many high-resourced languages with large amounts of speech data for training and evaluation, leaving low-resource languages relatively underdeveloped. While the CTC method has been successfully used for other languages, its effectiveness for the Sepedi language remains uncertain. In this study, we present the evaluation of the SepediEnglish code-switched automatic speech recognition system. This end-to-end system was developed using the Sepedi Prompted Code Switching corpus and the CTC approach. The performance of the system was evaluated using both the NCHLT Sepedi test corpus and the Sepedi Prompted Code Switching corpus. The model produced the lowest WER of 41.9%, however, the model faced challenges in recognizing the Sepedi only text

Code-Switching Automatic Speech Recognition for Nursing Record Documentation: System Development and Evaluation.

Taiwan has insufficient nursing resources due to the high turnover rate of health care providers. Therefore, reducing the heavy workload of these employees is essential. Herein, speech transcription, which has various potential clinical applications, was employed for the documentation of nursing records. The requirement of including only one speaker per transcription facilitated data collection and system development. Moreover, authorization from patients was unnecessary. The aim of this study was to construct a speech recognition system for nursing records such that health care providers can complete nursing records without typing or with only a few edits. Nursing records in Taiwan are mainly written in Mandarin, with technical terms and abbreviations presented in both Mandarin and English. Therefore, the training set consisted of English code-switching information. Next, transfer learning (TL) and meta-TL (MTL) methods, which perform favorably in code-switching scenarios, were applied. As of September 2021, the China Medical University Hospital Artificial Intelligence Speech (CMaiSpeech) data set was established by manually annotating approximately 100 hours of recordings from 525 speakers. The word error rate (WER) of the benchmark model of syllable-based TL was 29.54% in code-switching. The WER of the proposed model of syllable-based MTL was 22.20% in code-switching. The test set comprised 17,247 words. Moreover, in a clinical case, the proposed model of syllable-based MTL yielded a WER of 31.06% in code-switching. The clinical test set contained 1159 words. This paper has two main contributions. First, the CMaiSpeech data set-a Mandarin-English corpus-has been established. Health care providers in Taiwan are often compelled to use a mixture of Mandarin and English in nursing records. Second, an automatic speech recognition system for nursing record document conversion was proposed. The proposed system can shorten the work handover time and further reduce the workload of health care providers.

Improving N-Best Rescoring in Under-Resourced Code-Switched Speech Recognition Using Pretraining and Data Augmentation

In this study, we present improvements in N-best rescoring of code-switched speech achieved by n-gram augmentation as well as optimised pretraining of long short-term memory (LSTM) language models with larger corpora of out-of-domain monolingual text. Our investigation specifically considers the impact of the way in which multiple monolingual datasets are interleaved prior to being presented as input to a language model. In addition, we consider the application of large pretrained transformer-based architectures, and present the first investigation employing these models in English-Bantu code-switched speech recognition. Our experimental evaluation is performed on an under-resourced corpus of code-switched speech comprising four bilingual code-switched sub-corpora, each containing a Bantu language (isiZulu, isiXhosa, Sesotho, or Setswana) and English. We find in our experiments that, by combining n-gram augmentation with the optimised pretraining strategy, speech recognition errors are reduced for each individual bilingual pair by 3.51% absolute on average over the four corpora. Importantly, we find that even speech recognition at language boundaries improves by 1.14% even though the additional data is monolingual. Utilising the augmented n-grams for lattice generation, we then contrast these improvements with those achieved after fine-tuning pretrained transformer-based models such as distilled GPT-2 and M-BERT. We find that, even though these language models have not been trained on any of our target languages, they can improve speech recognition performance even in zero-shot settings. After fine-tuning on in-domain data, these large architectures offer further improvements, achieving a 4.45% absolute decrease in overall speech recognition errors and a 3.52% improvement over language boundaries. Finally, a combination of the optimised LSTM and fine-tuned BERT models achieves a further gain of 0.47% absolute on average for three of the four language pairs compared to M-BERT. We conclude that the careful optimisation of the pretraining strategy used for neural network language models can offer worthwhile improvements in speech recognition accuracy even at language switches, and that much larger state-of-the-art architectures such as GPT-2 and M-BERT promise even further gains.

A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition

A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition

Improving Transformer Based End-to-End Code-Switching Speech Recognition Using Language Identification

A Recurrent Neural Networks (RNN) based attention model has been used in code-switching speech recognition (CSSR). However, due to the sequential computation constraint of RNN, there are stronger short-range dependencies and weaker long-range dependencies, which makes it hard to immediately switch languages in CSSR. Firstly, to deal with this problem, we introduce the CTC-Transformer, relying entirely on a self-attention mechanism to draw global dependencies and adopting connectionist temporal classification (CTC) as an auxiliary task for better convergence. Secondly, we proposed two multi-task learning recipes, where a language identification (LID) auxiliary task is learned in addition to the CTC-Transformer automatic speech recognition (ASR) task. Thirdly, we study a decoding strategy to combine the LID into an ASR task. Experiments on the SEAME corpus demonstrate the effects of the proposed methods, achieving a mixed error rate (MER) of 30.95%. It obtains up to 19.35% relative MER reduction compared to the baseline RNN-based CTC-Attention system, and 8.86% relative MER reduction compared to the baseline CTC-Transformer system.

Pronunciation augmentation for Mandarin-English code-switching speech recognition

Code-switching (CS) refers to the phenomenon of using more than one language in an utterance, and it presents great challenge to automatic speech recognition (ASR) due to the code-switching property in one utterance, the pronunciation variation phenomenon of the embedding language words and the heavy training data sparse problem. This paper focuses on the Mandarin-English CS ASR task. We aim at dealing with the pronunciation variation and alleviating the sparse problem of code-switches by using pronunciation augmentation methods. An English-to-Mandarin mix-language phone mapping approach is first proposed to obtain a language-universal CS lexicon. Based on this lexicon, an acoustic data-driven lexicon learning framework is further proposed to learn new pronunciations to cover the accents, mis-pronunciations, or pronunciation variations of those embedding English words. Experiments are performed on real CS ASR tasks. Effectiveness of the proposed methods are examined on all of the conventional, hybrid, and the recent end-to-end speech recognition systems. Experimental results show that both the learned phone mapping and augmented pronunciations can significantly improve the performance of code-switching speech recognition.

Code-switched automatic speech recognition in five South African languages

Most automatic speech recognition (ASR) systems are optimised for one specific language and their performance consequently deteriorates drastically when confronted with multilingual or code-switched speech. We describe our efforts to improve an ASR system that can process code-switched South African speech that contains English and four indigenous languages: isiZulu, isiXhosa, Sesotho and Setswana. We begin using a newly developed language-balanced corpus of code-switched speech compiled from South African soap operas, which are rich in spontaneous code-switching. The small size of the corpus makes this scenario under-resourced, and hence we explore several ways of addressing this sparsity of data. We consider augmenting the acoustic training sets with in-domain data at the expense of making it unbalanced and dominated by English. We further explore the inclusion of monolingual out-of-domain data in the constituent languages. For language modelling, we investigate the inclusion of out-of-domain text data sources and also the inclusion of synthetically-generated code-switch bigrams. In our experiments, we consider two system architectures. The first considers four bilingual speech recognisers, each allowing code-switching between English and one of the indigenous languages. The second considers a single pentalingual speech recogniser able to process switching between all five languages. We find that the additional inclusion of each acoustic and text data source leads to some improvements. While in-domain data is substantially more effective, performance gains were also achieved using out-of-domain data, which is often much easier to obtain. We also find that improvements are achieved in all five languages, even when the training set becomes unbalanced and heavily skewed in favour of English. Finally, we find the use of TDNN-F architectures for the acoustic model to consistently outperform TDNN–BLSTM models in our data-sparse scenario.

Phonetic Variation Modeling and a Language Model Adaptation for Korean English Code-Switching Speech Recognition

In this paper, we propose a new method for code-switching (CS) automatic speech recognition (ASR) in Korean. First, the phonetic variations in English pronunciation spoken by Korean speakers should be considered. Thus, we tried to find a unified pronunciation model based on phonetic knowledge and deep learning. Second, we extracted the CS sentences semantically similar to the target domain and then applied the language model (LM) adaptation to solve the biased modeling toward Korean due to the imbalanced training data. In this experiment, training data were AI Hub (1033 h) in Korean and Librispeech (960 h) in English. As a result, when compared to the baseline, the proposed method improved the error reduction rate (ERR) by up to 11.6% with phonetic variant modeling and by 17.3% when semantically similar sentences were applied to the LM adaptation. If we considered only English words, the word correction rate improved up to 24.2% compared to that of the baseline. The proposed method seems to be very effective in CS speech recognition.

Exploration of End-to-End Framework for Code-Switching Speech Recognition Task: Challenges and Enhancements

The end-to-end (E2E) framework has emerged as a viable alternative to conventional hybrid systems in automatic speech recognition (ASR) domain. Unlike the monolingual case, the challenges faced by an E2E system in code-switching ASR task include (i) the expansion of target set to account for multiple languages involved, (ii) the requirement of a robust target-to-word (T2W) transduction, and (iii) the need for more effective context modeling. In this paper, we aim to address those challenges for reliable training of the E2E ASR system on a limited amount of code-switching data. The main contribution of this work lies in the E2E target set reduction by exploiting the acoustic similarity and the proposal of a novel context-dependent T2W transduction scheme. Additionally, a novel textual feature has been proposed to enhance the context modeling in the case of code-switching data. The experiments are performed on a recently created Hindi-English code-switching corpus. For contrast purposes, the existing combined target set based system is also evaluated. The proposed system outperforms the existing one and yields a target error rate of 18.1% along with a word error rate of 29.79%.

Automatic Speech Recognition of English-isiZulu Code-switched Speech from South African Soap Operas

We introduce a new English-isiZulu code-switched speech corpus compiled from South African soap opera broadcasts. isiZulu itself is currently under-resourced, and automatic speech recognition is made even more challenging by the high prevalence of code-switching in spontaneous speech. Analysis of the corpus reflects effects common in conversational isiZulu, such as vowel deletion and cross-language prefixes and suffixes. Baseline monolingual and code-switched automatic speech recognition systems are developed, including a new language model configuration that explicitly includes switching transitions. For code-switched speech, a system with language-dependent acoustic models and language-dependent language models linked by switching transitions leads to best performance, although word error rates overall remain very high.

Investigating Bilingual Deep Neural Networks for Automatic Recognition of Code-switching Frisian Speech

In this paper, a code-switching automatic speech recognition (ASR) system built for the Frisian language is described. Frisian is mostly spoken in the province Fryslân which is located in the north of the Netherlands. The native speakers of Frisian are mostly bilingual and often code-switch in daily conversations due to the extensive influence of the Dutch language. In the scope of the FAME! Project, the influence of this unforeseen language switching on modern ASR systems will be investigated with the objective of building a robust recognizer that can handle this phenomenon. For this purpose, in this work, we design a bilingual deep neural network (DNN)-based ASR system and investigate the impact of bilingual DNN training in the context of code-switching speech.

Chinese-English Phone Set Construction for Code-Switching ASR Using Acoustic and DNN-Extracted Articulatory Features

This study proposes a data-driven approach to phone set construction for code-switching automatic speech recognition (ASR). Acoustic and context-dependent cross-lingual articulatory features (AFs) are incorporated into the estimation of the distance between triphone units for constructing a Chinese-English phone set. The acoustic features of each triphone in the training corpus are extracted for constructing an acoustic triphone HMM. Furthermore, the articulatory features of the last/first state of the corresponding preceding/succeeding triphone in the training corpus are used to construct an AF-based GMM. The AFs, extracted using a deep neural network (DNN), are used for code-switching articulation modeling to alleviate the data sparseness problem due to the diverse context-dependent phone combinations in intra-sentential code-switching. The triphones are then clustered to obtain a Chinese-English phone set based on the acoustic HMMs and the AF-based GMMs using a hierarchical triphone clustering algorithm. Experimental results on code-switching ASR show that the proposed method for phone set construction outperformed other traditional methods.

Code-Switching Speech Detection Method by Combination of Language and Acoustic Information

In this paper, we propose a new speech detection method to English-Mandarin code-switching speech. Unlike previous methods, in this method we first train a support vector machine (SVM) model based on feature parameters and Gaussian Mixture Model (GMM) , then integrate the language identification (LID) information based on SVM model and acoustic information into the decoding process. Lastly, we develop a prototype system to present the method. Experiments proved that our method we can improve the accurancy of code-switching speech recognition at a certain degree compared with previous methods.