Related papers: Analyzing long-term rhythm variations in Mising an…
Fast Radio Bursts (FRBs), a class of millisecond-scale, highly energetic phenomena with unknown progenitors and radiation mechanisms, require proper statistical analysis as a key method for uncovering their mysteries. In this research, we…
Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the world. In this work,…
The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature--with inaccessible training data and code--poses major reproducibility…
Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple…
A deep neural network (DNN)-based model has been developed to predict non-parametric distributions of durations of phonemes in specified phonetic contexts and used to explore which factors influence durations most. Major factors in US…
Sound source localization (SSL) determines the position of sound sources using multi-channel audio data. It is commonly used to improve speech enhancement and separation. Extracting spatial features is crucial for SSL, especially in…
In the FAME! project, we aim to develop an automatic speech recognition (ASR) system for Frisian-Dutch code-switching (CS) speech extracted from the archives of a local broadcaster with the ultimate goal of building a spoken document…
A source separation method using a full-rank spatial covariance model has been proposed by Duong et al. ["Under-determined Reverberant Audio Source Separation Using a Full-rank Spatial Covariance Model," IEEE Trans. ASLP, vol. 18, no. 7,…
Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm,…
Affine frequency division multiplexing (AFDM) is a chirp-based multicarrier waveform that was recently proposed for communication over doubly dispersive channels. Given its chirp nature, AFDM is expected to have superior sensing…
This paper investigates the potential for large language models (LLMs) to develop private tonal languages for machine-to-machine (M2M) communication. Inspired by cryptophasia in human twins (affecting up to 50% of twin births) and natural…
Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…
This paper introduces a general and flexible framework for F0 and aperiodicity (additive non periodic component) analysis, specifically intended for high-quality speech synthesis and modification applications. The proposed framework…
Recent advancements in Text-to-Speech (TTS) technology have led to natural-sounding speech for English, primarily due to the availability of large-scale, high-quality web data. However, many other languages lack access to such resources,…
Automatic speech recognition (ASR) performance has improved drastically in recent years, mainly enabled by self-supervised learning (SSL) based acoustic models such as wav2vec2 and large-scale multi-lingual training like Whisper. A huge…
Synthetic data generated by text-to-speech (TTS) systems can be used to improve automatic speech recognition (ASR) systems in low-resource or domain mismatch tasks. It has been shown that TTS-generated outputs still do not have the same…
The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…
The syllable is a perceptually salient unit in speech. Since both the syllable and its acoustic correlate, i.e., the speech envelope, have a preferred range of rhythmicity between 4 and 8 Hz, it is hypothesized that theta-band neural…
This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among speaker characteristics, along with acoustic…
An auditory neuron can preserve the temporal fine structure of a low-frequency tone by phase-locking its response to the stimulus. Apart from sound localization, however, little is known about the role of this temporal information for…