17 citations · 21 across the 9 of their papers we have counts for
11 papers
Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction
Christophe Van Gysel, Maggie Wu, Lyan Verwimp +4
End-to-end (E2E) Automatic Speech Recognition (ASR) models are trained using paired audio-text samples that are expensive to obtain, since high-quality ground-truth data requires h…
Towards a World-English Language Model for On-Device Virtual Assistants
Rricha Jalota, Lyan Verwimp, Markus Nussbaum-Thom +3
Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally language-, region-, and in some cases, device-dependent, which increases the effort to scale and m…
Application-Agnostic Language Modeling for On-Device ASR
Markus Nußbaum-Thom, Lyan Verwimp, Youssef Oualil
On-device automatic speech recognition systems face several challenges compared to server-based systems. They have to meet stricter constraints in terms of speed, disk size and mem…
Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation
Thien Nguyen, Nathalie Tran, Liuhui Deng +16
Code-switching describes the practice of using more than one language in the same sentence. In this study, we investigate how to optimize a neural transducer based bilingual automa…
On the long-term learning ability of LSTM LMs
Wim Boes, Robbe Van Rompaey, Lyan Verwimp +3
We inspect the long-term learning ability of Long Short-Term Memory language models (LSTM LMs) by evaluating a contextual extension based on the Continuous Bag-of-Words (CBOW) mode…
Error-driven Pruning of Language Models for Virtual Assistants
Sashank Gondala, Lyan Verwimp, Ernest Pusateri +2
Language models (LMs) for virtual assistants (VAs) are typically trained on large amounts of data, resulting in prohibitively large models which require excessive memory and/or can…
Reverse Transfer Learning: Can Word Embeddings Trained for Different NLP Tasks Improve Neural Language Models?
Lyan Verwimp, Jerome R. Bellegarda
Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of th…
Information-Weighted Neural Cache Language Models for ASR
Lyan Verwimp, Joris Pelemans, Hugo Van hamme +1
Neural cache language models (LMs) extend the idea of regular cache language models by making the cache probability dependent on the similarity between the current context and the…
State Gradients for RNN Memory Analysis
Lyan Verwimp, Hugo Van hamme, Vincent Renkens +1
We present a framework for analyzing what the state in RNNs remembers from its input embeddings. Our approach is inspired by backpropagation, in the sense that we compute the gradi…
Language Models of Spoken Dutch
Lyan Verwimp, Joris Pelemans, Marieke Lycke +2
In Flanders, all TV shows are subtitled. However, the process of subtitling is a very time-consuming one and can be sped up by providing the output of a speech recognizer run on th…
Character-Word LSTM Language Models
Lyan Verwimp, Joris Pelemans, Hugo Van hamme +1
We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of p…