Recently, to mitigate the confusion between different languages in code-switching (CS) automatic speech recognition (ASR), the conditionally factorized models, such as the language-aware encoder (LAE), explicitly disregard the contextual information between different languages. However, this information may be helpful for ASR modeling. To alleviate this issue, we propose the LAE-ST-MoE framework. It incorporates speech translation (ST) tasks into LAE and utilizes ST to learn the contextual information between different languages. It introduces a task-based mixture of expert modules, employing separate feed-forward networks for the ASR and ST tasks. Experimental results on the ASRU 2019 Mandarin-English CS challenge dataset demonstrate that, compared to the LAE-based CTC, the LAE-ST-MoE model achieves a 9.26% mix error reduction on the CS test with the same decoding parameter. Moreover, the well-trained LAE-ST-MoE model can perform ST tasks from CS speech to Mandarin or English text.
Recent studies have demonstrated promising outcomes by employing large language models with multi-tasking capabilities. They utilize prompts to guide the model's behavior and surpass performance of task-specific models. Motivated by this, we ask: can we build a single model that jointly perform various spoken language understanding (SLU) tasks? To address this, we utilize pre-trained automatic speech recognition (ASR) models and employ various task and dataset specifiers as discrete prompts. We demonstrate efficacy of our single multi-task learning (MTL) model "UniverSLU" for 12 different speech classification and sequence generation tasks across 17 datasets and 9 languages. Results show that UniverSLU achieves competitive performance and even surpasses task-specific models. We also conduct preliminary investigations into enabling human-interpretable natural phrases instead of task specifiers as discrete prompts and test the model's generalization capabilities to new paraphrases.
We present a first large-scale public synthetic dataset for contextual spellchecking customization of automatic speech recognition (ASR) with focus on diverse rare and out-of-vocabulary (OOV) phrases, such as proper names or terms. The proposed approach allows creating millions of realistic examples of corrupted ASR hypotheses and simulate non-trivial biasing lists for the customization task. Furthermore, we propose injecting two types of ``hard negatives" to the simulated biasing lists in training examples and describe our procedures to automatically mine them. We report experiments with training an open-source customization model on the proposed dataset and show that the injection of hard negative biasing phrases decreases WER and the number of false alarms.
Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges. Unlike existing audio-visual speech enhance-ment challenges primarily focused on simulation data, the MISP 2023 challenge uniquely explores how front-end speech processing, combined with visual clues, impacts back-end tasks in real-world scenarios. This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the ac-curacy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments. This paper delivers a thorough overview of the task setting, dataset, and baseline system of the MISP 2023 challenge. It also includes an in-depth analysis of the challenges participants may encounter. The experimental results highlight the demanding nature of this task, and we look forward to the innovative solutions participants will bring forward.
Automatic speech recognition (ASR) models are typically trained on large datasets of transcribed speech. As language evolves and new terms come into use, these models can become outdated and stale. In the context of models trained on the server but deployed on edge devices, errors may result from the mismatch between server training data and actual on-device usage. In this work, we seek to continually learn from on-device user corrections through Federated Learning (FL) to address this issue. We explore techniques to target fresh terms that the model has not previously encountered, learn long-tail words, and mitigate catastrophic forgetting. In experimental evaluations, we find that the proposed techniques improve model recognition of fresh terms, while preserving quality on the overall language distribution.
The quality of automatic speech recognition (ASR) is typically measured by word error rate (WER). WER estimation is a task aiming to predict the WER of an ASR system, given a speech utterance and a transcription. This task has gained increasing attention while advanced ASR systems are trained on large amounts of data. In this case, WER estimation becomes necessary in many scenarios, for example, selecting training data with unknown transcription quality or estimating the testing performance of an ASR system without ground truth transcriptions. Facing large amounts of data, the computation efficiency of a WER estimator becomes essential in practical applications. However, previous works usually did not consider it as a priority. In this paper, a Fast WER estimator (Fe-WER) using self-supervised learning representation (SSLR) is introduced. The estimator is built upon SSLR aggregated by average pooling. The results show that Fe-WER outperformed the e-WER3 baseline relatively by 19.69% and 7.16% on Ted-Lium3 in both evaluation metrics of root mean square error and Pearson correlation coefficient, respectively. Moreover, the estimation weighted by duration was 10.43% when the target was 10.88%. Lastly, the inference speed was about 4x in terms of a real-time factor.
We introduce calamanCy, an open-source toolkit for constructing natural language processing (NLP) pipelines for Tagalog. It is built on top of spaCy, enabling easy experimentation and integration with other frameworks. calamanCy addresses the development gap by providing a consistent API for building NLP applications and offering general-purpose multitask models with out-of-the-box support for dependency parsing, parts-of-speech (POS) tagging, and named entity recognition (NER). calamanCy aims to accelerate the progress of Tagalog NLP by consolidating disjointed resources in a unified framework. The calamanCy toolkit is available on GitHub: https://github.com/ljvmiranda921/calamanCy.
We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally" across all spoken languages, referred to as speech attributes, namely manner and place of articulation. Specifically, several deterministic attribute-to-phoneme mapping matrices are constructed based on the predefined set of universal attribute inventory, which projects the knowledge-rich articulatory attribute logits, into output phoneme logits. The mapping puts knowledge-based constraints to limit inconsistency with acoustic-phonetic evidence in the integrated prediction. Combined with phoneme recognition, our phone recognizer is able to infer from both attribute and phoneme information. The proposed joint multilingual model is evaluated through phoneme recognition. In multilingual experiments over 6 languages on benchmark datasets LibriSpeech and CommonVoice, we find that our proposed solution outperforms conventional multilingual approaches with a relative improvement of 6.85% on average, and it also demonstrates a much better performance compared to monolingual model. Further analysis conclusively demonstrates that the proposed solution eliminates phoneme predictions that are inconsistent with attributes.
Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR).Although being able to obtain state-of-the-art (SOTA) performance, most of the studies are based on an autoregressive (AR) decoder which generates tokens one-by-one and results in a large real-time factor (RTF). To speed up inference, we introduce a recently proposed non-autoregressive model Paraformer as an acoustic model in the SA-ASR model.Paraformer uses a single-step decoder to enable parallel generation, obtaining comparable performance to the SOTA AR transformer models. Besides, we propose a speaker-filling strategy to reduce speaker identification errors and adopt an inter-CTC strategy to enhance the encoder's ability in acoustic modeling. Experiments on the AliMeeting corpus show that our model outperforms the cascaded SA-ASR model by a 6.1% relative speaker-dependent character error rate (SD-CER) reduction on the test set. Moreover, our model achieves a comparable SD-CER of 34.8% with only 1/10 RTF compared with the SOTA joint AR SA-ASR model.
Visual Speech Recognition (VSR) is a task to predict a sentence or word from lip movements. Some works have been recently presented which use audio signals to supplement visual information. However, existing methods utilize only limited information such as phoneme-level features and soft labels of Automatic Speech Recognition (ASR) networks. In this paper, we present a Multi-Temporal Lip-Audio Memory (MTLAM) that makes the best use of audio signals to complement insufficient information of lip movements. The proposed method is mainly composed of two parts: 1) MTLAM saves multi-temporal audio features produced from short- and long-term audio signals, and the MTLAM memorizes a visual-to-audio mapping to load stored multi-temporal audio features from visual features at the inference phase. 2) We design an audio temporal model to produce multi-temporal audio features capturing the context of neighboring words. In addition, to construct effective visual-to-audio mapping, the audio temporal models can generate audio features time-aligned with visual features. Through extensive experiments, we validate the effectiveness of the MTLAM achieving state-of-the-art performances on two public VSR datasets.