# The Performance Evaluation of Attention-Based Neural ASR under Mixed Speech Input

arXiv: https://arxiv.org/abs/2108.01245 · HTML: https://mlsanity.com/paper/2108.01245/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 3 Aug 2021.

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

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments](https://mlsanity.com/paper/1705.10874/) (2017)
- [Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation](https://mlsanity.com/paper/1502.04149/) (2015)
- [Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching](https://mlsanity.com/paper/1812.09323/) (2018)

## Built on by (most cited first, 1 of 1)

- [Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysis](https://mlsanity.com/paper/2501.06810/) (2025)

## Abstract (arXiv)

In order to evaluate the performance of the attention based neural ASR under noisy conditions, the current trend is to present hours of various noisy speech data to the model and measure the overall word/phoneme error rate (W/PER). In general, it is unclear how these models perform when exposed to a cocktail party setup in which two or more speakers are active. In this paper, we present the mixtures of speech signals to a popular attention-based neural ASR, known as Listen, Attend, and Spell (LAS), at different target-to-interference ratio (TIR) and measure the phoneme error rate. In particular, we investigate in details when two phonemes are mixed what will be the predicted phoneme; in this fashion we build a model in which the most probable predictions for a phoneme are given. We found a 65% relative increase in PER when LAS was presented with mixed speech signals at TIR = 0 dB and the performance approaches the unmixed scenario at TIR = 30 dB. Our results show the model, when presented with mixed phonemes signals, tend to predict those that have higher accuracies during evaluation of original phoneme signals.