Switchboard

The Switchboard dataset is an unlabeled target domain used to evaluate the performance of speech recognition systems, particularly in the context of unsupervised domain adaptation.

Papers using Switchboard (32)

Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition2026Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update2026Chain-of-Thought Training for Open E2E Spoken Dialogue Systems2025Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision2025Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition2021 · 76 citesNIST SRE CTS Superset: A large-scale dataset for telephony speaker recognition2021 · 20 citesEfficient Training of Neural Transducer for Speech Recognition2022 · 13 citesAdaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax2023 · 9 citesAdvancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers2021 · 4 citesToward Zero Oracle Word Error Rate on the Switchboard Benchmark2022 · 4 citesSvarah: Evaluating English ASR Systems on Indian Accents2023 · 3 citesProgressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training2024 · 2 citesImproving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition2021 · 1 citesASR4REAL: An extended benchmark for speech models2021 · 1 citesHMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch2022 · 1 citesDecoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation2023 · 1 citesDual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition2021Automatic Learning of Subword Dependent Model Scales2021Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models2022Generation of Speaker Representations Using Heterogeneous Training Batch Assembly2022PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations2022Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems2022Confidence Score Based Conformer Speaker Adaptation for Speech Recognition2022CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations2022Streaming Joint Speech Recognition and Disfluency Detection2022Speaker Adaptation for End-To-End Speech Recognition Systems in Noisy Environments2022Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition2022Analyzing And Improving Neural Speaker Embeddings for ASR2023Semi-Autoregressive Streaming ASR With Label Context2023Connecting Speech Encoder and Large Language Model for ASR2023Automatic Speech Recognition System-Independent Word Error Rate Estimation2024Improving Speech Recognition Error Prediction for Modern and Off-the-shelf Speech Recognizers2024