paper-with-me

Papers

What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis

2019-11-04 · Chung-Yi Li, Pei-Chieh Yuan, Hung-Yi Lee

End-to-end speech recognition systems have achieved competitive results compared to traditional systems. However, the complex transformations involved between layers given highly variable acoustic signals are hard to analyze. In this paper, we present our ASR probing model, which synthesizes speech from hidden representations of end-to-end ASR to examine the information maintain after each layer calculation. Listening to the synthesized speech, we observe gradual removal of speaker variability and noise as the layer goes deeper, which aligns with the previous studies on how deep network functions in speech recognition. This paper is the first study analyzing the end-to-end speech recognition model by demonstrating what each layer hears. Speaker verification and speech enhancement measurements on synthesized speech are also conducted to confirm our observation further.

📄 PDF Abstract BibTeX arXiv:1911.01102

Code (1)

YuanPJ/Voice-in-ASR

Tasks

Speaker VerificationSpeech Enhancementspeech-recognitionSpeech RecognitionSpeech Synthesis

Similar Papers 제목 키워드 기반

What Information Does a ResNet Compress?

2020-03-13 · ICLR 2019 5 · Luke Nicholas Darlow, Amos Storkey

The information bottleneck principle (Shwartz-Ziv & Tishby, 2017) suggests that SGD-based training of deep neural networks results in optimally compressed hidden layers, from an information theoretic perspective. However…

Trainable Reference-Based Evaluation Metric for Identifying Quality of English-Gujarati Machine Translation System

2025-09-27 · Nisheeth Joshi, Pragya Katyayan, Palak Arora arxiv

Machine Translation (MT) Evaluation is an integral part of the MT development life cycle. Without analyzing the outputs of MT engines, it is impossible to evaluate the performance of an MT system. Through experiments, it…

Machine Translation

Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System

2018-09-11 · WS 2018 11 · Barbara Rychalska, Dominika Basaj, Przemyslaw Biecek, Anna Wroblewska

In this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset. We show that main verbs in questions carry little influence on the decisions made…

Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality

2021-05-03 · NAACL 2021 4 · Hyun Gi Lee, Evan Sholle, Ashley Beecy, Subhi Al'Aref 외

Utilizing clinical texts in survival analysis is difficult because they are largely unstructured. Current automatic extraction models fail to capture textual information comprehensively since their labels are limited in …

Survival Analysis

Heart rate variability code: Does it exist and can we hack it?

2020-01-22 · Martin G. Frasch

Heart rate variability (HRV) has been studied for over 50 years, yet an integrative concept is missing on what HRV's mathematical properties represent physiologically. Here I introduce the notion of HRV code as an attemp…

Heart Rate Variability