Related papers: Autoencoding sensory substitution
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…
Speech activity detection (SAD) plays an important role in current speech processing systems, including automatic speech recognition (ASR). SAD is particularly difficult in environments with acoustic noise. A practical solution is to…
What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either…
Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is…
Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…
Sign language is a visual language that enhances communication between people and is frequently used as the primary form of communication by people with hearing loss. Even so, not many people with hearing loss use sign language, and they…
Despite renewed awareness of the importance of articulation, it remains a challenge for instructors to handle the pronunciation needs of language learners. There are relatively scarce pedagogical tools for pronunciation teaching and…
Many current deep learning approaches make extensive use of backbone networks pre-trained on large datasets like ImageNet, which are then fine-tuned to perform a certain task. In remote sensing, the lack of comparable large annotated…
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…
Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…
Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…
Different studies have shown the importance of visual cues throughout the speech perception process. In fact, the development of audiovisual approaches has led to advances in the field of speech technologies. However, although noticeable…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken…
Teacher-student (T/S) has shown to be effective for domain adaptation of deep neural network acoustic models in hybrid speech recognition systems. In this work, we extend the T/S learning to large-scale unsupervised domain adaptation of an…
At least 360 million people worldwide have disabling hearing loss that frequently causes difficulties in day-to-day conversations. Hearing aids often fail to offer enough benefits and have low adoption rates. However, people with hearing…
Assistive listening systems (ALSs) dramatically increase speech intelligibility and reduce listening effort. It is very likely that essentially everyone, not only individuals with hearing loss, would benefit from the increased…
We present an unsupervised approach that converts the input speech of any individual into audiovisual streams of potentially-infinitely many output speakers. Our approach builds on simple autoencoders that project out-of-sample data onto…
Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…