Building upon advancements in Large Language Models (LLMs), the field of audio processing has seen increased interest in training speech generation tasks with discrete speech token sequences.However, directly discretizing speech by neural audio codecs often results in sequences that fundamentally differ from text sequences.Unlike text, where text token sequences are deterministic, discrete speech tokens can exhibit significant variability based on contextual factors, while still producing perceptually identical audio segments.We refer to this phenomenon as Discrete Representation Inconsistency (DRI).This inconsistency can lead to a single speech segment being represented by multiple divergent sequences, which creates confusion in neural codec language models and results in poor generated speech.In this paper, we quantitatively analyze the DRI phenomenon within popular audio tokenizers such as En-Codec.Our approach effectively mitigates the DRI phenomenon of the neural audio codec.Furthermore, extensive experiments on the neural codec language model over LibriTTS and large-scale MLS dataset (44,000 hours) demonstrate the effectiveness and generality of our method.The demo of audio samples is available online 1 .

Recent advancements in speech large language models (SpeechLLMs) have attracted considerable attention. Nonetheless, current methods exhibit suboptimal performance in adhering to speech instructions. Notably, the intelligence of models significantly diminishes when processing speech-form input as compared to direct text-form input. Prior work has attempted to mitigate this semantic inconsistency between speech and text representations through techniques such as representation and behavior alignment, which involve the meticulous design of data pairs during the post-training phase. In this paper, we introduce a simple and scalable training method called InSerter, which stands for Interleaved Speech-Text Representation Pre-training. InSerter is designed to pre-train large-scale unsupervised speech-text sequences, where the speech is synthesized from randomly selected segments of an extensive text corpus using text-to-speech conversion. Consequently, the model acquires the ability to generate textual continuations corresponding to the provided speech segments, obviating the need for intensive data design endeavors. To systematically evaluate speech instruction-following capabilities, we introduce SpeechInstructBench, the first comprehensive benchmark specifically designed for speech-oriented instruction-following tasks. Our proposed model InSerter achieves SOTA performance in SpeechInstructBench and demonstrates superior or competitive results across diverse speech processing tasks.

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences of speech tokens, posing a significant challenge for downstream language models in long-context modeling. We observe that speech token sequences exhibit short-range dependency: due to the monotonic alignment between text and speech in text-to-speech (TTS) tasks, the prediction of the current token primarily relies on its local context, while long-range tokens contribute less to the current token prediction and often contain redundant information. Inspired by this observation, we propose a compressed-to-fine language modeling approach to address the challenge of long sequence speech tokens within neural codec language models: (1) Fine-grained Initial and Short-range Information: Our approach retains the prompt and local tokens during prediction to ensure text alignment and the integrity of paralinguistic information; (2) Compressed Long-range Context: Our approach compresses long-range token spans into compact representations to reduce redundant information while preserving essential semantics. Extensive experiments on various neural audio codecs and downstream language models validate the effectiveness and generalizability of the proposed approach, highlighting the importance of token compression in improving speech generation within neural codec language models. The demo of audio samples will be available at https://anonymous.4open.science/r/SpeechTokenPredictionViaCompressedToFinedLM.

Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text. This approach achieves fine-grained control over the temporal order, pitch, and energy of generated audio. To preserve the diversity of generation, we employ a trainable control condition encoder that is enhanced by a large language model and a trainable Fusion-Net to encode and fuse the additional conditions while keeping the weights of the pre-trained text-to-audio model frozen. Due to the lack of suitable datasets and evaluation metrics, we consolidate existing datasets into a new dataset comprising the audio and corresponding conditions and use a series of evaluation metrics to evaluate the controllability performance. Experimental results demonstrate that our model successfully achieves fine-grained control to accomplish controllable audio generation.

Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variability, using text prompts (descriptions) is more user-friendly since speech prompts can be hard to find or may not exist at all. TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech. In this work, we introduce PromptTTS 2 to address these challenges with a variation network to provide variability information of voice not captured by text prompts, and a prompt generation pipeline to utilize the large language models (LLM) to compose high quality text prompts. Specifically, the variation network predicts the representation extracted from the reference speech (which contains full information about voice variability) based on the text prompt representation. For the prompt generation pipeline, it generates text prompts for speech with a speech language understanding model to recognize voice attributes (e.g., gender, speed) from speech and a large language model to formulate text prompts based on the recognition results. Experiments on a large-scale (44K hours) speech dataset demonstrate that compared to the previous works, PromptTTS 2 generates voices more consistent with text prompts and supports the sampling of diverse voice variability, thereby offering users more choices on voice generation. Additionally, the prompt generation pipeline produces high-quality text prompts, eliminating the large labeling cost. The demo page of PromptTTS 2 is available (https://speechresearch.github.io/prompttts2).

Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features, into global ones, on which the contrastive loss is employed to reach coarse-grained cross-modal alignment. However, frame-level correspondence with texts may be ignored, making it ill-posed on explainability and fine-grained challenges which may also undermine performances on coarse-grained tasks. In this work, we aim to improve both coarse- and fine-grained audio-language alignment in large-scale contrastive pre-training. To unify the granularity and latent distribution of two modalities, a shared codebook is adopted to represent multi-modal global features with common bases, and each codeword is regularized to encode modality-shared semantics, bridging the gap between frame and word features. Based on it, a locality-aware block is involved to purify local patterns, and a hard-negative guided loss is devised to boost alignment. Experiments on eleven zero-shot coarse- and fine-grained tasks suggest that our model not only surpasses the baseline CLAP significantly but also yields superior or competitive results compared to current SOTA works.

Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utilizing text descriptions to guide speech synthesis. Thus, we develop a text-to-speech (TTS) system (dubbed as PromptTTS) that takes a prompt with both style and content descriptions as input to synthesize the corresponding speech. Specifically, PromptTTS consists of a style encoder and a content encoder to extract the corresponding representations from the prompt, and a speech decoder to synthesize speech according to the extracted style and content representations. Compared with previous works in controllable TTS that require users to have acoustic knowledge to understand style factors such as prosody and pitch, PromptTTS is more user-friendly since text descriptions are a more natural way to express speech style (e.g., "A lady whispers to her friend slowly"). Given that there is no TTS dataset with prompts, to benchmark the task of PromptTTS, we construct and release a dataset containing prompts with style and content information and the corresponding speech. Experiments show that PromptTTS can generate speech with precise style control and high speech quality. Audio samples and our dataset are publicly available1.