Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In this paper, we present SLM-S2ST, a multimodal LM for direct speech-to-speech translation (S2ST), built on the opensource Phi4-MM model. SLM-S2ST extends its predecessor by generating translated speech using an audio transformer head that predicts audio tokens with a delay relative to text tokens, followed by a streaming vocoder for waveform synthesis. Our experimental results on the CVSS-C dataset demonstrate SLMS2ST’s superior performance, significantly surpassing existing baseline models trained on the same dataset. Furthermore, when we scale up the training data and the model size, SLM-S2ST reaches on-par performance with the current SOTA model.

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in performance, efficiency, and alignment quality. In this work, we systematically compare representative joint speech-text decoding strategies—including the interleaved, and parallel generation paradigms—under a controlled experimental setup using the same base language model, speech tokenizer and training data. Our results show that the interleaved approach achieves the best alignment. However it suffers from slow inference due to long token sequence length. To address this, we propose a novel early-stop interleaved (ESI) pattern that not only significantly accelerates decoding but also yields slightly better performance. Additionally, we curate high-quality question answering (QA) datasets to further improve speech QA performance.

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they’re developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the target language are often pseudo labels due to the prohibitive cost of manual ST data labeling. In this paper, we introduce a methodology named Connectionist Temporal Classification guided modality matching (CTC-GMM) that enhances the streaming ST model by leveraging extensive machine translation (MT) text data. This technique employs CTC to compress the speech sequence into a compact embedding sequence that matches the corresponding text sequence, allowing us to utilize matched source-target language text pairs from the MT corpora to refine the streaming ST model further. Our evaluations with FLEURS and CoVoST2 show that the CTC-GMM approach can increase translation accuracy relatively by 13.9% and 6.4% respectively, while also boosting decoding speed by 59.7% on GPU.

Non-autoregressive automatic speech recognition (NASR) models have gained attention due to their parallelism and fast inference. The encoder-based NASR, e.g. connectionist temporal classification (CTC), can be initialized from the speech foundation models (SFM) but does not account for any dependencies among intermediate tokens. The encoder-decoder-based NASR, like CTC alignment-based single-step non-autoregressive transformer (CASS-NAT), can mitigate the dependency problem but is not able to efficiently integrate SFM. Inspired by the success of recent work of speech-text joint pre-training with a shared transformer encoder, we propose a new encoder-based NASR, UniEnc-CASSNAT, to combine the advantages of CTC and CASS-NAT. UniEnc-CASSNAT consists of only an encoder as the major module, which can be the SFM. The encoder plays the role of both the CASS-NAT encoder and decoder by two forward passes. The first pass of the encoder accepts the speech signal as input, while the concatenation of the speech signal and the token-level acoustic embedding is used as the input for the second pass. Examined on the Librispeech 100h, MyST, and Aishell1 datasets, the proposed UniEnc-CASSNAT achieves state-of-the-art NASR results and is better or comparable to CASS-NAT with only an encoder and hence, fewer model parameters. Our codes1are publicly available.

In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the model training with the Connectionist Temporal Classification (CTC) objective after removing duplicated IDs in each masked region. The idea stems from the observation that there can be significant errors in alignments when using clustered or aligned IDs. CTC learns alignments implicitly, indicating that learning with CTC can be more flexible when misalignment exists. We examine CTCBERT on IDs from HuBERT Iter1, HuBERT Iter2, and PBERT. The CTC training brings consistent improvements compared to the CE training. Furthermore, when loading blank-related parameters during finetuning, slight improvements are observed. Evaluated on the Librispeech 960-100h setting, the relative WER improvements of CTCBERT are 2%-11% over HuBERT and PERT on test-other data.

Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. Autoregressive transformers, variants of AED, adopt an autoregressive mechanism for token generation and thus are relatively slow during inference. In this paper, we present a comprehensive study of a CTC Alignment-based Single-Step Non-Autoregressive Transformer (CASS-NAT) for end-to-end ASR. In CASS-NAT, word embeddings in the autoregressive transformer (AT) are substituted with token-level acoustic embeddings (TAE) that are extracted from encoder outputs with the acoustical boundary information offered by the CTC alignment. TAE can be obtained in parallel, resulting in a parallel generation of output tokens. During training, Viterbi-alignment is used for TAE generation, and multiple training strategies are further explored to improve the word error rate (WER) performance. During inference, an error-based alignment sampling method is investigated in depth to reduce the alignment mismatch in the training and testing processes. Experimental results show that the CASS-NAT has a WER that is close to AT on various ASR tasks, while providing a$\sim$24x inference speedup. With and without self-supervised learning, we achieve new state-of-the-art results for non-autoregressive models on several datasets. We also analyze the behavior of the CASS-NAT decoder to explain why it can perform similarly to AT. We find that TAEs have similar functionality to word embeddings for grammatical structures, which might indicate the possibility of learning some semantic information from TAEs without a language model.

This paper proposes a novel linear prediction coding-based data augmentation method for children’s low and zero resource dialect ASR. The data augmentation procedure consists of perturbing the formant peaks of the LPC spectrum during LPC analysis and reconstruction. The method is evaluated on two novel children’s speech datasets with one containing California English from the Southern California Area and the other containing a mix of Southern American English and African American English from the Atlanta, Georgia area. We test the proposed method in training both an HMM-DNN system and an end-to-end system to show model-robustness and demonstrate that the algorithm improves ASR performance, especially for zero resource dialect children’s task, as compared to common data augmentation methods such as VTLP, Speed Perturbation, and SpecAugment.

Children’s automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model might overfit to the training data, and hence good starting points for training are essential. Recently, meta-learning was proposed to learn model initialization (MI) for ASR tasks of different languages. This method leads to good performance when the model is adapted to an unseen language. How-ever, MI is vulnerable to overfitting on training tasks (learner overfitting). It is also unknown whether MI generalizes to other low-resource tasks. In this paper, we validate the effectiveness of MI in children’s ASR and attempt to alleviate the problem of learner overfitting. To achieve model-agnostic meta-learning (MAML), we regard children’s speech at each age as a different task. In terms of learner overfitting, we propose a task-level augmentation method by simulating new ages using frequency warping techniques. Detailed experiments are conducted to show the impact of task augmentation on each age for kindergarten-aged speech. As a result, our approach achieves a relative word error rate (WER) improvement of 51% over the baseline system with no augmentation or initialization.

Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models trained through SSL are biased to the pretraining data which is usually different from the data used in finetuning tasks, causing a domain shifting problem, and thus resulting in limited knowledge transfer. We propose a novel framework, domain responsible adaptation and finetuning (DRAFT), to reduce domain shifting in pretrained speech models through an additional adaptation stage. In DRAFT, residual adapters (RAs) are inserted in the pretrained model to learn domain-related information with the same SSL loss as the pretraining stage. Only RA parameters are updated during the adaptation stage. DRAFT is agnostic to the type of SSL method used and is evaluated with three widely used approaches: APC, Wav2vec2.0, and HuBERT. On two child ASR tasks (OGI and MyST databases), using SSL models trained with un-annotated adult speech data (Librispeech), relative WER improvements of up to 19.7% are observed when compared to the pretrained models without adaptation. Additional experiments examined the potential of cross knowledge transfer between the two datasets and the results are promising, showing a broader usage of the proposed DRAFT framework.

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children’s automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to alleviate this problem is model pre-training using data from adult speech. Pre-training can be done using supervised (SPT) or unsupervised methods, depending on the availability of annotations. Typically, SPT performs better. In this paper, we focus on UPT to address the situations when pre-training data are unlabeled. Autoregressive predictive coding (APC), a UPT method, predicts frames from only one direction, limiting its use to uni-directional pre-training. Conventional bidirectional UPT methods, however, predict only a small portion of frames. To extend the benefits of APC to bi-directional pre-training, Bi-APC is proposed. We then use adaptation techniques to transfer knowledge learned from adult speech (using the Librispeech corpus) to child speech (OGI Kids corpus). LSTM-based hybrid systems are investigated. For the uni-LSTM structure, APC obtains similar WER improvements to SPT over the baseline. When applied to BLSTM, however, APC is not as competitive as SPT, but our proposed Bi-APC has comparable improvements to SPT.

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of acoustics for each token. The information are used to extract acoustic representation for each token in parallel, referred to as token-level acoustic embedding which substitutes the word embedding in autoregressive transformer (AT) to achieve parallel generation in decoder. During inference, an error-based alignment sampling method is proposed to be applied to the CTC output space, reducing the WER and retaining the parallelism as well. Experimental results show that the proposed method achieves WERs of 3.8%/9.1% on Librispeech test clean/other dataset without an external LM, and a CER of 5.8% on Aishell1 Mandarin corpus, respectively1. Compared to the AT baseline, the CASS-NAT has a performance reduction on WER, but is 51.2x faster in terms of RTF. When decoding with an oracle CTC alignment, the lower bound of WER without LM reaches 2.3% on the test-clean set, indicating the potential of the proposed method.

Automatic speech recognition (ASR) systems for young children are needed due to the importance of age-appropriate educational technology. Because of the lack of publicly available young child speech data, feature extraction strategies such as feature normalization and data augmentation must be considered to successfully train child ASR systems. This study proposes a novel technique for child ASR using both feature normalization and data augmentation methods based on the relationship between formants and fundamental frequency (fo). Both the fofeature normalization and data augmentation techniques are implemented as a frequency shift in the Mel domain. These techniques are evaluated on a child read speech ASR task. Child ASR systems are trained by adapting a BLSTM-based acoustic model trained on adult speech. Using both fonormalization and data augmentation results in a relative word error rate (WER) improvement of 19.3% over the baseline when tested on the OGI Kids’ Speech Corpus, and the resulting child ASR system achieves the best WER currently reported on this corpus.

Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT) has shown a large real time factor (RTF) improvement over autoregressive transformers (AT). In this work, we propose several methods to improve the accuracy of the end-to-end CASS-NAT, followed by performance analyses. First, convolution augmented self-attention blocks are applied to both the encoder and decoder modules. Second, we propose to expand the trigger mask (acoustic boundary) for each token to increase the robustness of CTC alignments. In addition, iterated loss functions are used to enhance the gradient update of low-layer parameters. Without using an external language model, the WERs of the improved CASS-NAT, when using the three methods, are 3.1%/7.2% on Librispeech test clean/other sets and the CER is 5.4% on the Aishell1 test set, achieving a 7%~21% relative WER/CER improvement. For the analyses, we plot attention weight distributions in the decoders to visualize the relationships between token-level acoustic embeddings. When the acoustic embeddings are visualized, we find that they have a similar behavior to word embeddings, which explains why the improved CASS-NAT performs similarly to AT.

This paper describes the SPAPL system for the INTER-SPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German.∼ 5 hours of transcribed data and ∼ 60 hours of untranscribed data are provided to develop a German ASR system for children.For the training of the transcribed data, we propose a non-speech state discriminative loss (NSDL) to mitigate the influence of long-duration non-speech segments within speech utterances.In order to explore the use of the untranscribed data, various approaches are implemented and combined together to incrementally improve the system performance.First, bidirectional autoregressive predictive coding (Bi-APC) is used to learn initial parameters for acoustic modelling using the provided untranscribed data.Second, incremental semi-supervised learning is further used to iteratively generate pseudo-transcribed data.Third, different data augmentation schemes are used at different training stages to increase the variability and size of the training data.Finally, a recurrent neural network language model (RNNLM) is used for rescoring.Our system achieves a word error rate (WER) of 39.68% on the evaluation data, an approximately 12% relative improvement over the official baseline (45.21%).

In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive predictive coding (APC) encoder is pre-trained in an unsupervised manner using both out-of-domain (LibriSpeech, VoxCeleb) and in-domain (DeepMine) unlabeled datasets to learn generic, high-level feature representation that encapsulates speaker and phonetic content. Two task-specific decoders were trained using labeled datasets to classify speakers (SID) and phrases (PID). Speaker embeddings extracted from the SID decoder were scored using a PLDA. SID and PID systems were fused at the score level. There is a 51.9% relative improvement in minDCF for our system compared to the fully supervised x-vector baseline on the cross-lingual DeepMine dataset. However, the i-vector/HMM method outperformed the proposed APC encoder-decoder system. A fusion of the x-vector/PLDA baseline and the SID/PLDA scores prior to PID fusion further improved performance by 15% indicating complementarity of the proposed approach to the x-vector system. We show that the proposed approach can leverage from large, unlabeled, data-rich domains, and learn speech patterns independent of downstream tasks. Such a system can provide competitive performance in domain-mismatched scenarios where test data is from data-scarce domains.

Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition.In previous work, researchers have shown that such architectures can acquire comparable results to state-of-the-art ASR systems, especially when using a bidirectional encoder and global soft attention (GSA) mechanism.However, bidirectional encoder and GSA are two obstacles for real-time speech recognition.In this work, we aim to stream LAS baseline by removing the above two obstacles.On the encoder side, we use a latency-controlled (LC) bidirectional structure to reduce the delay of forward computation.Meanwhile, an adaptive monotonic chunk-wise attention (AMoChA) mechanism is proposed to replace GSA for the calculation of attention weight distribution.Furthermore, we propose two methods to alleviate the huge performance degradation when combining LC and AMoChA.Finally, we successfully acquire an online LAS model, LC-AMoChA, which has only 3.5% relative performance reduction to LAS baseline on our internal Mandarin corpus.