Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

Automatic speech and language technologies are still heavily biased toward high-resource languages, limiting their applicability to dialectal and low-resource settings such as Algerian Dialect. This language presents additional challenges including lack of standardized orthography, frequent codeswitching with French, and scarcity of annotated speech resources. This paper addresses the problem of building a complete speech-to-speech conversational system for Algerian Dialect. We propose a modular pipeline integrating automatic speech recognition, natural language understanding, retrieval-augmented generation, and text-to-speech synthesis within a unified architecture. This work is the continuation of our previous work on Algerian dialectal conversational systems Bechiri and Lanasri [2026], extending it from text-based dialogue modeling to full speech-based interaction. We constructed dedicated datasets for ASR, NLU, and TTS in the telecom domain and fine-tune pretrained models for each component. The ASR system is built on Whisper-based adaptation, while the NLU module combines transformer-based embeddings with a task-oriented dialogue framework. A neural TTS system is trained on a newly collected dialectal corpus to enable spoken response generation. Experimental results show strong performance across all components, including low word error rate for ASR, high intent classification and entity recognition scores for NLU, and stable speech synthesis quality. The proposed system provides a reproducible baseline for end-to-end conversational modeling in Algerian Dialect.

Systematic Study of Dysarthric Speech Recognition: Spectral Features and Acoustic Models

The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65\% relative improvement in isolated word recognition and a 4.63\% relative improvement in sentence recognition for dysarthric speech, compared to previous research. This improvement effectively compensates for speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.

DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognition

Automatic Speech Recognition (ASR) often degrades in real-world noisy environments, making noise robustness essential for deployment. Supervised noise-augmented fine-tuning is a common remedy, but it can introduce a robustness-clean trade-off and overfit to specific corruptions, degrading recognition in clean conditions. We propose DASH, a self-distillation framework that improves robustness by learning clean--noisy consistency from paired views. DASH distills hidden representations from multiple encoder layers to capture features from low-level acoustics to high-level semantics, and stabilizes training by minimizing KL divergence between prototype assignment distributions of clean and noisy views. Experiments on LibriSpeech show that DASH consistently improves recognition under diverse noisy conditions while preserving clean accuracy, achieved by a label-free pre-training stage with minimal additional overhead (about 4% of fine-tuning time) beyond standard fine-tuning.

Scaling Audio Models Efficiently: A Joint Study of Compute Constraints and Optimization Behavior

In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER). We propose a unified framework that analyzes three fundamental compute dimensions: model size ($x_N$), input length ($x_T$), and representation resolution ($x_V$). Motivated by recent advances in compute optimal scaling for multimodal models, we systematically vary these dimensions to examine their influence on task performance under fixed computational budgets. Our study provides insights into how compute resources can be optimally distributed across model capacity, temporal context, and representational granularity, offering practical guidelines for the design of efficient speech models. Through experiments on LibriSpeech and CREMA-D datasets, we demonstrate non-linear scaling behavior and identify optimal operating points. Our results show that (1) increasing model size yields diminishing returns: scaling Tiny (39M) to Small (244M) reduces WER by 8.22%, whereas Small to Medium (769M) reduces WER by only 2.35%; (2) an optimal audio duration of approximately 4 seconds exists for SER; and (3) reducing encoder token resolution provides an effective mechanism for lowering inference cost, Large-v3 (1540M) with 750 frames requires 2572 GFLOPS whereas with 1500 frames requires 5228 GFLOPS, with less than 3% relative increase in WER. Additionally, LoRA-based adaptation enables efficient finetuning with minimal performance degradation.

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis

Reviewing recorded interviews for affective cues such as composure, hesitation and agitation is slow and subjective, and cloud services that could automate it require sensitive audio to leave the device. EmotionAI is a fully local Computational Intelligence (CI) pipeline that couples Speech Emotion Recognition (SER) with generative reasoning. Speaker diarisation, Whisper Automatic Speech Recognition (ASR) and a wav2vec2 emotion classifier produce per-segment affective evidence, which is then passed to an adversarial three-model local Large Language Model (LLM) panel for timestamp-grounded and citation-constrained question answering. Zero-shot evaluation on the RAVDESS four-class English subset (n = 672) exposes cross-corpus fragility rather than classifier superiority: the deployed classifier scores 48.8% accuracy, above random (24.9%) and majority (28.6%) baselines but below an in-domain MFCC + logistic-regression comparator (71.0%). The complete pipeline runs in a mean 157 s on CPU (real-time factor approximately 1.33) with zero external calls. The contribution is not state-of-the-art SER but an auditable, privacy-preserving integration of imperfect affective evidence into grounded conversational analysis, together with an honest empirical account of where cross-corpus transfer and human-centred validation still fall short.

HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems

End-to-end Automatic Speech Recognition (ASR) systems hallucinate on natural speech, yet existing mitigation methods are typically evaluated on non-speech or artificially corrupted audio. We introduce HALAS, the first human-annotated dataset of naturally occurring hallucinations from seven state-of-the-art ASR models on real unprocessed earnings call recordings. HALAS provides span-level labels, enabling analysis of hallucination patterns and their severity. Our analysis reveals strong cross-model vocabulary overlap and confirms that hallucinations also occur for almost correctly transcribed speech (characterized by a low Word Error Rate). The proposed benchmark with HALAS shows that the character and semantic-level metrics used as a proxy for hallucination detection reach 81% ROC-AUC, while state-of-the-art detection methods achieve an F1 score of only 53.1%. As such, HALAS establishes the first rigorous non-artificial benchmark for the detection and mitigation of ASR hallucinations.

Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American English

Self-supervised and supervised speech models are increasingly used to investigate which linguistic information their internal representations encode, and at what level of abstraction they encode it. One underexplored phenomenon is consonant cluster reduction (CCR) in African American English (AAE), a widespread phonological process and a source of automatic speech recognition (ASR) disparity. To examine how CCR is represented, we conduct speaker-independent layer-wise probing of wav2vec2-base and Whisper-small using two tasks: segmental reduction detection and segmental restoration of underlying cluster identity. Both models distinguish reduced and canonical forms with high accuracy. Crucially, reduced segments retain cues to their underlying stops, indicating that CCR is encoded as structured gradient phonological variation rather than simple segmental deletion. These results demonstrate structured phonological encoding of AAE CCR patterns in modern speech models.

Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition

Non-autoregressive (NAR) decoding generates output tokens in parallel, making speech recognition faster than autoregressive decoding, which generates them sequentially from left to right. However, the recognition performance is degraded because NAR decoding cannot resolve uncertainty by conditioning on previously generated tokens. To address this issue, we propose a novel NAR decoding framework based on minimum Bayes' risk (MBR) decoding, termed NAR-MBR decoding, that maximizes the expected utility calculated from samples drawn from the output probability of an NAR model rather than maximizing the output probability. Notably, by leveraging the nature of NAR models, multiple samples are obtained efficiently with a single forward computation. Our experiments across LibriSpeech, Switchboard, AMI, and web presentation corpus demonstrated that our NAR-MBR decoding outperformed previous NAR decoding and ran faster than AR decoding.

Audio--Image Alignment as a Continued-Pretraining Stage Improves Low-Resource ASR

Thousands of languages are spoken worldwide, yet many remain under-resourced for Automatic Speech Recognition (ASR) due to the limited availability of high-quality transcribed speech data. Collecting accurate transcriptions is often costly and labor-intensive, particularly for low-resource languages. In this work, we investigate the use of aligned audio-image pairs to adapt pretrained audio encoders without requiring transcription data before supervised fine-tuning. Our proposed representation alignment stage is introduced between large-scale pretraining and supervised ASR fine-tuning. Specifically, image representations extracted from pretrained vision encoders are aligned with audio representations to further adapt a pretrained audio encoder. For this alignment process, we utilize the Vaani dataset, in which images serve as prompts for speech collection, naturally providing paired audio-image data. We evaluate the proposed approach using multiple vision encoders and a pretrained FastConformer audio encoder. Experimental results demonstrate that models fine-tuned after representation alignment consistently achieve improved ASR performance compared to direct fine-tuning. These findings highlight the potential of audio-image representation alignment as an effective transcription-free adaptation strategy for enhancing ASR systems in low-resource language settings.

Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demonstrate that SER models can be reliably compromised with high attack success rates under low poisoning ratios, while maintaining near-clean performance on benign inputs. We further show that backdoor patterns exhibit strong cross-model transferability and that self-supervised representations are particularly susceptible to learning these triggers. These findings reveal that TTS technology dramatically lowers the barrier to effective backdoor attacks, exposing critical vulnerabilities in modern SER pipelines and motivating the urgent need for dedicated defenses.