Analysis and Tuning of a Voice Assistant System for Dysfluent Speech

Systematic Review of Machine Learning Approaches for Detecting Developmental Stuttering

“…Work conducted after the closing date of this systematic review suggests that deep learning techniques may further improve automatic classification of stuttering [23] [64]. Further work is needed to confirm whether modern deep methods can allow advances in performance as seen in other fields such as computer vision [65].…”

From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition

“…2.1.3 Dysfluent Speech Recognition. Technical work on improving speech assistants for PWS has focused on ASR models [8,23,31,35,50,51,61], stuttering detection [43], dysfluency detection or classification [22,40,42,48,56], clinical assessment [11], and dataset development [12,37,42,55]. Shonibare et al [61] and Mendelev et al [50] investigate training end-to-end RNN-T ASR models on speech from PWS.…”

“…Alharbi et al [2,3] focused on stuttered speech from kids that incorporates the structure of repetitions and other dyfluencies into an augmented language model that is better at including dysfluencies in a transcription. In our work, we focus on solutions, like Mitra et al's [51], which can be applied on top of existing recognition systems and do not require as much data as end-to-end solutions. Their VA-oriented approach was to optimize a small set of ASR decoder parameters on stuttered speech, such that the system is biased towards common VA phrases, and was effective in removing dysfluencies such as repetitions in speech.…”

“…Research on speech technology for PWS has largely focused on technical improvements to automatic speech recognition (ASR) models [31,35,50,51,61], dysfluency detection [22,40,42,48], and dataset development [12,37,42,55]. This body of work has largely lacked a human-centered approach to understanding the experiences that PWS have with speech recognition systems [17], which could in turn inform how to prioritize and advance technical improvements.…”

“…However, people with more moderate or severe patterns encountered high truncation (e.g., > 20%) and word error rates (13.6% to 49.2%)-which is also reflected by many survey participants. Motivated by these results, we describe and evaluate three technical solutions (two new and one previously published [51]) that apply production-oriented improvements to a consumer-grade ASR system. These solutions reduce truncation rates by 79.1% and improve word error rates in transcribed speech from 25.4% to 9.9% for a set of participants with moderate to severe dysfluent speech.…”