Related papers: Pseudo Label Is Better Than Human Label

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

Currently, machine learning techniques have seen significant success across various applications. Most of these techniques rely on supervision from human-generated labels or a mixture of noisy and imprecise labels from multiple sources.…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared with its forerunners, the proposed method uses pronunciation…

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is…

Automatic speech recognition (ASR) has made remarkable progress but heavily relies on large-scale labeled data, which is scarce for low-resource languages like Vietnamese. While existing systems such as Whisper, USM, and MMS achieve…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU…

Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely…

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…

Semi-supervised learning (SSL) is an active area of research which aims to utilize unlabelled data in order to improve the accuracy of speech recognition systems. The current study proposes a methodology for integration of two key ideas: 1)…

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the…

In this work we evaluate the utility of synthetic data for training automatic speech recognition (ASR). We use the ASR training data to train a text-to-speech (TTS) system similar to FastSpeech-2. With this TTS we reproduce the original…

We present a method for cross-lingual training an ASR system using absolutely no transcribed training data from the target language, and with no phonetic knowledge of the language in question. Our approach uses a novel application of a…