Related papers: A Comparison of Semi-Supervised Learning Technique…

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…

Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual…

Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training. In this work, we leverage…

There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training and deployment for both use cases. While in real-world ASR…

Streaming end-to-end automatic speech recognition (ASR) systems are widely used in everyday applications that require transcribing speech to text in real-time. Their minimal latency makes them suitable for such tasks. Unlike their…

Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous…

In this paper, we perform an exhaustive evaluation of different representations to address the intent classification problem in a Spoken Language Understanding (SLU) setup. We benchmark three types of systems to perform the SLU intent…

Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several…

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

Semi-supervised learning is a promising way to reduce the annotation cost for text-classification. Combining with pre-trained language models (PLMs), e.g., BERT, recent semi-supervised learning methods achieved impressive performance. In…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

Self-supervised learning (SSL) has been able to leverage unlabeled data to boost the performance of automatic speech recognition (ASR) models when we have access to only a small amount of transcribed speech data. However, this raises the…