Related papers: Cross-lingual Knowledge Transfer and Iterative Pse…

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

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…

In this paper, we propose to improve end-to-end (E2E) spoken language understand (SLU) in an RNN transducer model (RNN-T) by incorporating a joint self-conditioned CTC automatic speech recognition (ASR) objective. Our proposed model is akin…

Research on automatic speech recognition (ASR) systems for electrolaryngeal speakers has been relatively unexplored due to small datasets. When training data is lacking in ASR, a large-scale pretraining and fine tuning framework is often…

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

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…

Building a multilingual Automated Speech Recognition (ASR) system in a linguistically diverse country like India can be a challenging task due to the differences in scripts and the limited availability of speech data. This problem can be…

End-to-end Automatic Speech Recognition (ASR) systems are rapidly claiming to become state-of-art over other modeling methods. Several techniques have been introduced to improve their ability to handle multiple languages. However, due to…

This paper presents a novel donor data selection method to enhance low-resource automatic speech recognition (ASR). While ASR performs well in high-resource languages, its accuracy declines in low-resource settings due to limited training…

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…

Automatic Speech Recognition (ASR) performance for low-resource languages is still far behind that of higher-resource languages such as English, due to a lack of sufficient labeled data. State-of-the-art methods deploy self-supervised…

Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

This work explores better adaptation methods to low-resource languages using an external language model (LM) under the framework of transfer learning. We first build a language-independent ASR system in a unified sequence-to-sequence (S2S)…

Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language identity is seldom known beforehand in real-world scenarios, it…

The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions. The performance of such systems has been shown to drop…

User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques for reducing the latency for both components, the automatic…

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…

Multilingual speech recognition has drawn significant attention as an effective way to compensate data scarcity for low-resource languages. End-to-end (e2e) modelling is preferred over conventional hybrid systems, mainly because of no…