paper-with-me

홈 › Papers

Towards Improved Room Impulse Response Estimation for Speech Recognition

2022-11-08 · Anton Ratnarajah, Ishwarya Ananthabhotla, Vamsi Krishna Ithapu, Pablo Hoffmann, Dinesh Manocha, Paul Calamia

We propose a novel approach for blind room impulse response (RIR) estimation systems in the context of a downstream application scenario, far-field automatic speech recognition (ASR). We first draw the connection between improved RIR estimation and improved ASR performance, as a means of evaluating neural RIR estimators. We then propose a generative adversarial network (GAN) based architecture that encodes RIR features from reverberant speech and constructs an RIR from the encoded features, and uses a novel energy decay relief loss to optimize for capturing energy-based properties of the input reverberant speech. We show that our model outperforms the state-of-the-art baselines on acoustic benchmarks (by 17\% on the energy decay relief and 22\% on an early-reflection energy metric), as well as in an ASR evaluation task (by 6.9\% in word error rate).

📄 PDF Abstract BibTeX arXiv:2211.04473

Code (1)

anton-jeran/Speech2RIR pytorch

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Generative Adversarial NetworkRoom Impulse Response (RIR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Dereverberation using joint estimation of dry speech signal and acoustic system

2020-07-24 · Sanna Wager, Keunwoo Choi, Simon Durand

The purpose of speech dereverberation is to remove quality-degrading effects of a time-invariant impulse response filter from the signal. In this report, we describe an approach to speech dereverberation that involves jo…

Room Impulse Response (RIR)Speech Dereverberation

RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification

2024-06-05 · Jacob Bitterman, Daniel Levi, Hilel Hagai Diamandi, Sharon Gannot 외

This paper focuses on room fingerprinting, a task involving the analysis of an audio recording to determine the specific volume and shape of the room in which it was captured. While it is relatively straightforward to de…

Contrastive Learning

dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processing

2021-04-27 · Diego Di Carlo, Pinchas Tandeitnik, Cédric Foy, Antoine Deleforge 외

This paper presents dEchorate: a new database of measured multichannel Room Impulse Responses (RIRs) including annotations of early echo timings and 3D positions of microphones, real sources and image sources under diffe…

BenchmarkingRetrievalRoom Impulse Response (RIR)Speech Enhancement

Blind estimation of room acoustic parameters from speech signals based on extended model of room impulse response

2022-12-26 · Lijun Wang, Suradej Duangpummet, Masashi Unoki

The speech transmission index (STI) and room acoustic parameters (RAPs), which are derived from a room impulse response (RIR), such as reverberation time and early decay time, are essential to assess speech transmission …

Room Impulse Response (RIR)

Blind Identification of Binaural Room Impulse Responses from Smart Glasses

2024-03-28 · Thomas Deppisch, Nils Meyer-Kahlen, Sebastià V. Amengual Garí

Smart glasses are increasingly recognized as a key medium for augmented reality, offering a hands-free platform with integrated microphones and non-ear-occluding loudspeakers to seamlessly mix virtual sound sources into …