Kyle Kastner

Gary Wang, Kyle Kastner, Ankur Bapna et al.

Recently, a number of approaches to train speech models by incorpo-rating text into end-to-end models have been developed, with Mae-stro advancing state-of-the-art automatic speech recognition (ASR)and Speech Translation (ST) performance. In this paper, we expandour understanding of the resulting shared speech-text representationswith two types of analyses. First we examine the limits of speech-free domain adaptation, finding that a corpus-specific duration modelfor speech-text alignment is the most important component for learn-ing a shared speech-text representation. Second, we inspect the sim-ilarities between activations of unimodal (speech or text) encodersas compared to the activations of a shared encoder. We find that theshared encoder learns a more compact and overlapping speech-textrepresentation than the uni-modal encoders. We hypothesize that thispartially explains the effectiveness of the Maestro shared speech-textrepresentations.

Kyle Kastner, Aaron Courville

This paper introduces R-MelNet, a two-part autoregressive architecture with a frontend based on the first tier of MelNet and a backend WaveRNN-style audio decoder for neural text-to-speech synthesis. Taking as input a mixed sequence of characters and phonemes, with an optional audio priming sequence, this model produces low-resolution mel-spectral features which are interpolated and used by a WaveRNN decoder to produce an audio waveform. Coupled with half precision training, R-MelNet uses under 11 gigabytes of GPU memory on a single commodity GPU (NVIDIA 2080Ti). We detail a number of critical implementation details for stable half precision training, including an approximate, numerically stable mixture of logistics attention. Using a stochastic, multi-sample per step inference scheme, the resulting model generates highly varied audio, while enabling text and audio based controls to modify output waveforms. Qualitative and quantitative evaluations of an R-MelNet system trained on a single speaker TTS dataset demonstrate the effectiveness of our approach.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Hyun Jin Park, Dhruuv Agarwal, Neng Chen et al.

This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amount of training data to be accurate, and obtaining such training data can be costly. In the current state of the art, TTS models can generate large amounts of natural-sounding data, which can help reducing cost and time for KWS model development. Still, TTS generated data can be lacking diversity compared to real data. To pursue maximizing KWS model accuracy under the constraint of limited resources and current TTS capability, we explored various strategies to mix TTS data and real human speech data, with a focus on minimizing real data use and maximizing diversity of TTS output. Our experimental results indicate that relatively small amounts of real audio data with speaker diversity (100 speakers, 2k utterances) and large amounts of TTS synthesized data can achieve reasonably high accuracy (within 3x error rate of baseline), compared to the baseline (trained with 3.8M real positive utterances).

Hyun Jin Park, Dhruuv Agarwal, Neng Chen et al.

The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speech (TTS) synthesized data can reduce the cost and time associated with KWS development. However, TTS data may contain artifacts not present in real speech, which the KWS model can exploit (overfit), leading to degraded accuracy on real speech. To address this issue, we propose applying an adversarial training method to prevent the KWS model from learning TTS-specific features when trained on large amounts of TTS data. Experimental results demonstrate that KWS model accuracy on real speech data can be improved by up to 12% when adversarial loss is used in addition to the original KWS loss. Surprisingly, we also observed that the adversarial setup improves accuracy by up to 8%, even when trained solely on TTS and real negative speech data, without any real positive examples.

Francesco Visin, Marco Ciccone, Adriana Romero et al.

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally and vertically in both directions, encoding patches or activations, and providing relevant global information. Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features. Upsampling layers follow ReNet layers to recover the original image resolution in the final predictions. The proposed ReSeg architecture is efficient, flexible and suitable for a variety of semantic segmentation tasks. We evaluate ReSeg on several widely-used semantic segmentation datasets: Weizmann Horse, Oxford Flower, and CamVid; achieving state-of-the-art performance. Results show that ReSeg can act as a suitable architecture for semantic segmentation tasks, and may have further applications in other structured prediction problems. The source code and model hyperparameters are available on https://github.com/fvisin/reseg.

Yusong Wu, Tim Cooijmans, Kyle Kastner et al.

Jamming requires coordination, anticipation, and collaborative creativity between musicians. Current generative models of music produce expressive output but are not able to generate in an \emph{online} manner, meaning simultaneously with other musicians (human or otherwise). We propose ReaLchords, an online generative model for improvising chord accompaniment to user melody. We start with an online model pretrained by maximum likelihood, and use reinforcement learning to finetune the model for online use. The finetuning objective leverages both a novel reward model that provides feedback on both harmonic and temporal coherency between melody and chord, and a divergence term that implements a novel type of distillation from a teacher model that can see the future melody. Through quantitative experiments and listening tests, we demonstrate that the resulting model adapts well to unfamiliar input and produce fitting accompaniment. ReaLchords opens the door to live jamming, as well as simultaneous co-creation in other modalities.

Christopher Li, Gary Wang, Kyle Kastner et al.

Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc. Previous work has shown that recall can be improved by retrieving rewrite candidates from a large database of likely, contextually-relevant alternatives to the hypothesis text using nearest-neighbors search over embeddings of the ASR hypothesis text to correct and candidate corrections. However, ASR-hypothesis-based retrieval can yield poor precision if the textual hypotheses are too phonetically dissimilar to the transcript truth. In this paper, we eliminate the hypothesis-audio mismatch problem by querying the correction database directly using embeddings derived from the utterance audio; the embeddings of the utterance audio and candidate corrections are produced by multimodal speech-text embedding networks trained to place the embedding of the audio of an utterance and the embedding of its corresponding textual transcript close together. After locating an appropriate correction candidate using nearest-neighbor search, we score the candidate with its speech-text embedding distance before adding the candidate to the original n-best list. We show a relative word error rate (WER) reduction of 6% on utterances whose transcripts appear in the candidate set, without increasing WER on general utterances.

Yusong Wu, Ethan Manilow, Yi Deng et al.

Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive controls, but at the cost of realism. Black-box neural audio synthesis and concatenative samplers can produce realistic audio, but have few mechanisms for control. In this work, we introduce MIDI-DDSP a hierarchical model of musical instruments that enables both realistic neural audio synthesis and detailed user control. Starting from interpretable Differentiable Digital Signal Processing (DDSP) synthesis parameters, we infer musical notes and high-level properties of their expressive performance (such as timbre, vibrato, dynamics, and articulation). This creates a 3-level hierarchy (notes, performance, synthesis) that affords individuals the option to intervene at each level, or utilize trained priors (performance given notes, synthesis given performance) for creative assistance. Through quantitative experiments and listening tests, we demonstrate that this hierarchy can reconstruct high-fidelity audio, accurately predict performance attributes for a note sequence, independently manipulate the attributes of a given performance, and as a complete system, generate realistic audio from a novel note sequence. By utilizing an interpretable hierarchy, with multiple levels of granularity, MIDI-DDSP opens the door to assistive tools to empower individuals across a diverse range of musical experience.

Johanna Hansen, Kyle Kastner, Aaron Courville et al.

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.

Kyle Kastner, Rithesh Kumar, Tim Cooijmans et al.

We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(2017). Recomposition (Casal & Casey, 2010) focuses on reworking existing musical pieces, adhering to structure at a high level while also re-imagining other aspects of the work. This can involve reuse of pre-existing themes or parts of the original piece, while also requiring the flexibility to generate new content at different levels of granularity. Applying the aforementioned modeling pipeline to recomposition, we show diverse and structured generation conditioned on chord sequence annotations.

Kyle Kastner, João Felipe Santos, Yoshua Bengio et al.

Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical deployment, as direct control of pronunciation is crucial in certain cases. We demonstrate a simple method for combining multiple types of linguistic information in a single encoder, named representation mixing, enabling flexible choice between character, phoneme, or mixed representations during inference. Experiments and user studies on a public audiobook corpus show the efficacy of our approach.

Ankesh Anand, Eugene Belilovsky, Kyle Kastner et al.

We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question by intelligently navigating in a simulated environment, gathering necessary visual information only through first-person vision before finally answering. Consequently, a blindfold baseline which ignores the environment and visual information is a degenerate solution, yet we show through our experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.

Amjad Almahairi, Kyle Kastner, Kyunghyun Cho et al.

Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased flexibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model's ability to act as a regularizer of the product representations.

Eugene Belilovsky, Kyle Kastner, Gaël Varoquaux et al.

We consider structure discovery of undirected graphical models from observational data. Inferring likely structures from few examples is a complex task often requiring the formulation of priors and sophisticated inference procedures. Popular methods rely on estimating a penalized maximum likelihood of the precision matrix. However, in these approaches structure recovery is an indirect consequence of the data-fit term, the penalty can be difficult to adapt for domain-specific knowledge, and the inference is computationally demanding. By contrast, it may be easier to generate training samples of data that arise from graphs with the desired structure properties. We propose here to leverage this latter source of information as training data to learn a function, parametrized by a neural network that maps empirical covariance matrices to estimated graph structures. Learning this function brings two benefits: it implicitly models the desired structure or sparsity properties to form suitable priors, and it can be tailored to the specific problem of edge structure discovery, rather than maximizing data likelihood. Applying this framework, we find our learnable graph-discovery method trained on synthetic data generalizes well: identifying relevant edges in both synthetic and real data, completely unknown at training time. We find that on genetics, brain imaging, and simulation data we obtain performance generally superior to analytical methods.

Junyoung Chung, Kyle Kastner, Laurent Dinh et al.

In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN)1 can model the kind of variability observed in highly structured sequential data such as natural speech. We empirically evaluate the proposed model against related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the RNN dynamic hidden state.

Francesco Visin, Kyle Kastner, Kyunghyun Cho et al.

In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on three widely-used benchmark datasets; MNIST, CIFAR-10 and SVHN. The result suggests that ReNet is a viable alternative to the deep convolutional neural network, and that further investigation is needed.