# BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge

arXiv: https://arxiv.org/abs/2101.12729 · HTML: https://mlsanity.com/paper/2101.12729/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 29 Jan 2021.

## Builds on (most cited first, 5 of 5)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Wav2Letter: an End-to-End ConvNet-based Speech Recognition System](https://mlsanity.com/paper/1609.03193/) (2016)

## Built on by (most cited first, 2 of 2)

- [Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation](https://mlsanity.com/paper/2210.15226/) (2022)
- [Hystoc: Obtaining word confidences for fusion of end-to-end ASR systems](https://mlsanity.com/paper/2305.12579/) (2023)

## Abstract (arXiv)

This paper describes joint effort of BUT and Telef'onica Research on development of Automatic Speech Recognition systems for Albayzin 2020 Challenge. We compare approaches based on either hybrid or end-to-end models. In hybrid modelling, we explore the impact of SpecAugment layer on performance. For end-to-end modelling, we used a convolutional neural network with gated linear units (GLUs). The performance of such model is also evaluated with an additional n-gram language model to improve word error rates. We further inspect source separation methods to extract speech from noisy environment (i.e. TV shows). More precisely, we assess the effect of using a neural-based music separator named Demucs. A fusion of our best systems achieved 23.33% WER in official Albayzin 2020 evaluations. Aside from techniques used in our final submitted systems, we also describe our efforts in retrieving high quality transcripts for training.