相关论文: Leveraging supplementary text data to kick-start a…

High quality transcription data is crucial for training automatic speech recognition (ASR) systems. However, the existing industry-level data collection pipelines are expensive to researchers, while the quality of crowdsourced transcription…

In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio…

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…

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…

Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Psychoacoustic studies have shown that locally-time reversed (LTR) speech, i.e., signal samples time-reversed within a short segment, can be accurately recognised by human listeners. This study addresses the question of how well a…

We introduce a novel and inexpensive approach for the temporal alignment of speech to highly imperfect transcripts from automatic speech recognition (ASR). Transcripts are generated for extended lecture and presentation videos, which in…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

In the FAME! project, we aim to develop an automatic speech recognition (ASR) system for Frisian-Dutch code-switching (CS) speech extracted from the archives of a local broadcaster with the ultimate goal of building a spoken document…

Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently,…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

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…

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…

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more…

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous…