LVLyan Verwimp

Lyan Verwimp

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lyan Verwimp has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction

    by Christophe Van Gysel, Maggie Wu, Lyan Verwimp, Caglar Tirkaz, Marco Bertola, Zhihong Lei, Youssef Oualil

    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 human annotators. Voice search applications, such as digital media players, leverage ASR to allow users to search by voice as opposed to an on-screen keyboard. However, recent or infrequent movie titles may not be sufficiently represented in the E2E ASR system's training data, and hence, may suffer poor recognition. In this paper, we propose a phonetic correction system that consists of (a) a phonetic search based on the ASR model's output that generates phonetic alternatives that may not be considered by the E2E system, and (b) a rescorer component that combines the ASR model recognition and the phonetic alternatives, and select a final system output. We find that our approach improves word error rate between 4.4 and 7.6% relative on benchmarks of popular movie titles over a series of competitive baselines.

  • Open Access

    Application-Agnostic Language Modeling for On-Device ASR

    by 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 memory while maintaining the same accuracy. Often they have to serve several applications with different distributions at once, such as communicating with a virtual assistant and speech-to-text. The simplest solution to serve multiple applications is to build application-specific (language) models, but this leads to an increase in memory. Therefore, we explore different data- and architecture-driven language modeling approaches to build a single application-agnostic model. We propose two novel feed-forward architectures that find an optimal trade off between different on-device constraints. In comparison to the application-specific solution, one of our novel approaches reduces the disk size by half, while maintaining speed and accuracy of the original model.