Related papers: Comparing phonemes and visemes with DNN-based lipr…
Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training…
Vision-Language Models (VLMs) have rapidly advanced alongside Large Language Models (LLMs). This study evaluates the capabilities of prominent generative VLMs, such as GPT-4.1 and Gemini 2.5 Pro, accessed via APIs, for histopathology image…
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or…
In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian Consonant-Vowel Combination (PCVC) speech dataset. Nowadays, deep neural networks play a crucial role in classification tasks. However, the…
Visual Speech Recognition (VSR) stands at the intersection of computer vision and speech recognition, aiming to interpret spoken content from visual cues. A prominent challenge in VSR is the presence of homophenes-visually similar lip…
Several training strategies and temporal models have been recently proposed for isolated word lip-reading in a series of independent works. However, the potential of combining the best strategies and investigating the impact of each of them…
The rapid spread of multilingual misinformation requires robust automated fact verification systems capable of handling fine-grained veracity assessments across diverse languages. While large language models have shown remarkable…
Ultrasound tongue imaging (UTI) is a non-invasive and cost-effective tool for studying speech articulation, motor control, and related disorders. However, real-time tongue contour segmentation remains challenging due to low signal-to-noise…
For text-independent short-utterance speaker recognition (SUSR), the performance often degrades dramatically. This paper presents a combination approach to the SUSR tasks with two phonetic-aware systems: one is the DNN-based i-vector system…
When reading lips, many people benefit from additional visual information from the lip movements of the speaker, which is, however, very error prone. Algorithms for lip reading with artificial intelligence based on artificial neural…
Previous studies have confirmed the effectiveness of incorporating visual information into speech enhancement (SE) systems. Despite improved denoising performance, two problems may be encountered when implementing an audio-visual SE (AVSE)…
The human visual system provides us with a rich and meaningful percept of the world, transforming retinal signals into visuo-semantic representations. For a model of these representations, here we leveraged a combination of two currently…
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…
Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems…
Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…
Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft…
In this work, we re-think the task of speech enhancement in unconstrained real-world environments. Current state-of-the-art methods use only the audio stream and are limited in their performance in a wide range of real-world noises. Recent…
Recent works have explored deep architectures for learning multimodal speech representation (e.g. audio and images, articulation and audio) in a supervised way. Here we investigate the role of combining different speech modalities, i.e.…
Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques as input (e.g. ultrasound tongue imaging, MRI, lip video). The advantage of lip video is that it is easily…
Phoneme recognition is a very important part of speech recognition that requires the ability to extract phonetic features from multiple frames. In this paper, we compare and analyze CNN, RNN, Transformer, and Conformer models using phoneme…