相关论文: Generative Adversarial Training Data Adaptation fo…

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…

While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the…

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of…

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…

Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work…

The prevalence of automatic speech recognition (ASR) systems in spoken language applications has increased significantly in recent years. Notably, many African languages lack sufficient linguistic resources to support the robustness of…

Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with…

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has…

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…

This study investigates the performance of personalized automatic speech recognition (ASR) for recognizing disordered speech using small amounts of per-speaker adaptation data. We trained personalized models for 195 individuals with…

Many archival recordings of speech from endangered languages remain unannotated and inaccessible to community members and language learning programs. One bottleneck is the time-intensive nature of annotation. An even narrower bottleneck…

Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population. Open-sourced ASR systems, trained on sufficient data from adults, are…

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages,…

We present an analysis of semi-supervised acoustic and language model training for English-isiZulu code-switched ASR using soap opera speech. Approximately 11 hours of untranscribed multilingual speech was transcribed automatically using…

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…

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often…

Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch…

Language endangerment poses a major challenge to linguistic diversity worldwide, and technological advances have opened new avenues for documentation and revitalization. Among these, automatic speech recognition (ASR) has shown increasing…

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory,…