相关论文: FAST-RIR: Fast neural diffuse room impulse respons…
The machine recognition of speech spoken at a distance from the microphones, known as far-field automatic speech recognition (ASR), has received a significant increase of attention in science and industry, which caused or was caused by an…
Recurrent neural networks (RNNs) are becoming the de facto solution for speech recognition. RNNs exploit long-term temporal relationships in data by applying repeated, learned transformations. Unlike fully-connected (FC) layers with single…
Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…
Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and…
The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility…
An acoustic reverberator consisting of a network of delay lines connected via scattering junctions is proposed. All parameters of the reverberator are derived from physical properties of the enclosure it simulates. It allows for simulation…
Room impulse response estimation is essential for tasks like speech dereverberation, which improves automatic speech recognition. Most existing methods rely on either statistical signal processing or deep neural networks designed to…
This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…
We introduce a novel algorithm for online estimation of acoustic impulse responses (AIRs) which allows for fast convergence by exploiting prior knowledge about the fundamental structure of AIRs. The proposed method assumes that the…
Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such…
Any audio recording encapsulates the unique fingerprint of the associated acoustic environment, namely the background noise and reverberation. Considering the scenario of a room equipped with a fixed smart speaker device with one or more…
The rise of generative AI for tasks like Automatic Speech Recognition (ASR) has created a critical energy consumption challenge. While ASICs offer high efficiency, they lack the programmability to adapt to evolving algorithms. To address…
This paper presents the time-domain wideband spherical microphone array impulse response generator (TDW-SMIR generator), which is a time-domain wideband image source method (ISM) for generating the room impulse responses captured by an open…
Acoustic environment characterization opens doors for sound reproduction innovations, smart EQing, speech enhancement, hearing aids, and forensics. Reverberation time, clarity, and direct-to-reverberant ratio are acoustic parameters that…
In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…
Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important…
Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched, resulting in increased effectiveness. However, existing…
We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…
The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…
Most often, virtual acoustic rendering employs real-time updated room acoustic simulations to accomplish auralization for a variable listener perspective. As an alternative, we propose and test a technique to interpolate room impulse…