28 citations · 38 across the 9 of their papers we have counts for
12 papers
On the Effectiveness of Speech Self-supervised Learning for Music
Yinghao Ma, Ruibin Yuan, Yizhi Li +12
Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR…
Leveraging Cross-Utterance Context For ASR Decoding
Robert Flynn, Anton Ragni
While external language models (LMs) are often incorporated into the decoding stage of automated speech recognition systems, these models usually operate with limited context. Cros…
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Yizhi Li, Ruibin Yuan, Ge Zhang +17
Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Althoug…
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning
Yizhi Li, Ruibin Yuan, Ge Zhang +11
The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it still remains unexplored how to build a framework for lea…
HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models
Yizhi Li, Ge Zhang, Bohao Yang +4
Fairness has become a trending topic in natural language processing (NLP), which addresses biases targeting certain social groups such as genders and religions. However, regional b…
Approximate Fixed-Points in Recurrent Neural Networks
Zhengxiong Wang, Anton Ragni
Recurrent neural networks are widely used in speech and language processing. Due to dependency on the past, standard algorithms for training these models, such as back-propagation…
Continuous representations of intents for dialogue systems
Sindre André Jacobsen, Anton Ragni
Intent modelling has become an important part of modern dialogue systems. With the rapid expansion of practical dialogue systems and virtual assistants, such as Amazon Alexa, Apple…
Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks
Alexandros Kastanos, Anton Ragni, Mark Gales
Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-ena…
Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks
Anton Ragni, Qiujia Li, Mark Gales +1
The standard approach to assess reliability of automatic speech transcriptions is through the use of confidence scores. If accurate, these scores provide a flexible mechanism to fl…
Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
Qiujia Li, Preben Ness, Anton Ragni +1
The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these…
Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription
Yu Wang, Xie Chen, Mark Gales +2
State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as…
Future Word Contexts in Neural Network Language Models
Xie Chen, Xunying Liu, Anton Ragni +2
Recently, bidirectional recurrent network language models (bi-RNNLMs) have been shown to outperform standard, unidirectional, recurrent neural network language models (uni-RNNLMs)…