相关论文: Study of Phonemes Confusions in Hierarchical Autom…
This research presents a novel approach to enhancing automatic speech recognition systems by integrating noise detection capabilities directly into the recognition architecture. Building upon the wav2vec2 framework, the proposed method…
Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…
Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without…
Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. Acoustic landmark…
Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical…
Speech command recognition (SCR) has been commonly used on resource constrained devices to achieve hands-free user experience. However, in real applications, confusion among commands with similar pronunciations often happens due to the…
We consider the problem of precision matrix estimation where, due to extraneous confounding of the underlying precision matrix, the data are independent but not identically distributed. While such confounding occurs in many scientific…
Automatic pronunciation assessment is a major component of a computer-assisted pronunciation training system. To provide in-depth feedback, scoring pronunciation at various levels of granularity such as phoneme, word, and utterance, with…
Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not…
We present a phoneme-level analysis of automatic speech recognition (ASR) for two low-resourced and phonologically complex East Caucasian languages, Archi and Rutul, based on curated and standardized speech-transcript resources totaling…
Human perception of surrounding events is strongly dependent on audio cues. Thus, acoustic insulation can seriously impact situational awareness. We present an exploratory study in the domain of assistive computing, eliciting requirements…
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…
This research explores how the information of prompts interacts with the high-performing speech recognition model, Whisper. We compare its performances when prompted by prompts with correct information and those corrupted with incorrect…
We investigate what linguistic factors affect the performance of Automatic Speech Recognition (ASR) models. We hypothesize that orthographic and phonological complexities both degrade accuracy. To examine this, we fine-tune the multilingual…
Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of…
We are at an exciting time for machine lipreading. Traditional research stemmed from the adaptation of audio recognition systems. But now, the computer vision community is also participating. This joining of two previously disparate areas…
Repetition is a basic indicator of musical structure. This study introduces new algorithms for identifying musical phrases based on repetition. Phrases combine to form sections yielding a two-level hierarchical structure. Automatically…
We investigate a surprising limitation of LLMs: their inability to consistently generate text in a user's desired language. We create the Language Confusion Benchmark (LCB) to evaluate such failures, covering 15 typologically diverse…
Homograph disambiguation, the task of distinguishing words with identical spellings but different meanings, poses a substantial challenge in natural language processing. In this study, we introduce a novel dataset tailored for Persian…
In the field of software engineering, applying language models to the token sequence of source code is the state-of-art approach to build a code recommendation system. The syntax tree of source code has hierarchical structures. Ignoring the…