Waves Maxx® Voice
Waves Maxx® Voice Features
Voice Experience Input Processing
MaxxEC eliminates echoes common in online communication improving intelligibility of speakers experiencing feedback, including that disruptive echo of your own voice. Echo occurs when the microphone picks up sound from the speakers, causing users to hear themselves through their remote device. MaxxEC frees you from annoying echoes so your conversations can flow. After all, saying it once is enough.
For manufacturers, a primary cause of echoes is feedback, in which the microphone picks up sounds coming from your device’s speaker. To minimize this effect, MaxxEC uses an adaptive filter to identify sounds that come from the device’s speakers and cancels them out. As a full duplex echo canceler. MaxxEC also uses advanced non-linear modeling to reduce harmonic distortion sounds and other residuals that the adaptive filer can’t predict. In essence, MaxxEC eliminates the need make hardware changes in order to reposition microphones that cause feedback.
MaxxBeam offers directional noise reduction technology for integrated microphones that intelligently overcomes noisy environments and focuses on you (or other speakers) for improved voice clarity and intelligibility in noisy environments. MaxxBeam uses multiple microphones to determine the direction from which the speaker talks and then cancels out noises coming from other directions. MaxxBeam’s Auto Beam enables the beam to track and locate the main speech source, giving users the freedom and flexibility to communicate from almost anywhere. Auto Beam also controls the width and scope of the beam, automatically adjusting to one or more user’s positions to improve the clarity of multiple speakers or a single speaker on the move.
For manufacturers, MaxxBeam offers tremendous microphone placement flexibility. It can work with any array of microphones, or with any matching microphones. MaxxBeam is perfect for consumer-grade microphones as its Automatic Microphone Calibration can compensate for differences in microphone pairs. Best of all, MaxxBeam simplifies hardware design and is compatible with a wide variety of microphone types, improving any device’s VoIP and Voice Assistance capabilities.
MaxxNR intelligently recognizes and eliminates undesirable background frequencies while upholding the sound of your natural voice for clearer, quieter, and better sounding online communication. This applies both to your own voice, as well as the voices you’re listening to.
For Manufacturers, MaxxNR uses adaptive multi-band dynamics with zero latency or phase distortion. This results in a transparent, natural sound without annoying background noise in devices developed for the exponentially growing VoIP and Voice Assistance market.
MaxxEQ is an elegant, easy-to-use equalizer that can be automatically or manually adjusted in order to enrich your unique voice for clarity and quality of sound.
For manufacturers, MaxxEQ’s intuitive paragraphic user interface makes click-and-drag adjustments to enhance audio quality on any device quick and efficient.
Since all voices are different, AutoEQ intelligently recognizes unique vocal qualities and optimizes them for intelligibility and clarity to deliver the most optimal vocal tone.
For manufacturers, AutoEQ is a reference EQ designed to shape any user’s voice into an audible, optimized profile. This feature can compensate for lack of low-end, mitigate harsh midrange frequencies, and enhance high-end frequencies while reducing noise to add clarity and intelligibility.
Using a powerful combination of compression, gating, and leveling, MaxxVolume ensures a strong and steady vocal input to your microphone for more intelligible and clear communication.
For manufacturers, the small microphones used in portable devices typically have limited input capabilities, especially when it comes to the diversity of the human voice. To optimize microphone performance for VoIP and Voice Assistance, Waves took our all-in-one dynamics processor, MaxxVolume, and configured it specifically for voice input.
DeKey intelligently eliminates disruptive clicking noises made by typing and keystrokes during meetings. You or anyone you converse with can finally type away during online conversations without disrupting communication and peace of mind.
For Manufacturers, communicating directly with your device’s operating system, DeKey isolates telltale keystroke noises and removes them without affecting voices. Additionally, DeKey understands that not all clicks are the same and constantly adapts to sounds in order to improve affectivity. This gives end-users a keystroke, click-free experience that doesn’t affect the voice experience your device delivers.
VoIP applications transmit a great deal of information using a minimum amount of bandwidth. Unwanted vocal sounds are not only annoying, they take up limited resources. As a result, voices can sound unpleasant and hard to understand. A common source of this is sibilance, the loud “ss” and “sh” sounds that come from common words. Sibilance overloads sound processors and masks voices. DeEsser intelligently analyses the frequencies of sibilance and removes them, reducing hissing sounds and producing more intelligible, clear, and pleasant vocal quality during online communication.
For manufacturers, DeEsser acutely reduces sibilance, which saves bandwidth resources in order to focus on delivering end-users the VoIP and Voice Assistance experience your device was designed for.
Voice & Speech Input Processing
MaxxEC overcomes one of the most challenging scenarios for ASR feedback caused when media is played back by a device’s internal speakers that are usually located much closer to the microphone(s) than the user. Unlike monophonic echo cancellers designed for voice calls, MaxxEC Stereo was designed specifically for ASR. It eliminates intrusive sound from content like music, movies and games. MaxxEC Stereo effectively cancels out any and all sounds produced from a computer’s speakers and can handle true stereo leaks.
For manufacturers, MaxxEC makes continuous real-time adjustments in response to the media being played, as well as changes in the user’s environment. With MaxxEC Stereo, users can listen to music, watch movies, and play games, while simultaneously and effectively communicating with their devices. This eliminates the need to reposition microphones or speakers in smart communication and assistance devices.
Voice isolator is a diffused noise attenuator, allowing Voice Assistance applications to accurately identify user commands in crowded areas. Noisy environments cause a reduction in the efficiency of speech recognition engines. Using a direction-sensitive filter optimized for automatic speech recognition, Voice Isolator detects and tracks the main speech source and then assumes all other speech-like sources are unwanted crowd noise.
For manufacturers, Voice Isolator’s directional filter has been trained on ASR engines for maximum Command Acceptance Rate and minimum Word Error Rate in order to improve your smart device’s Voice Assistance capabilities and functionality. Additionally, Voice Isolator operates in real-time by applying a combination of linear and non-linear directional filters. Both are controlled by the detected direction of speech, and then some of the frequencies in the unwanted noise and speech sources are suppressed to minimize their affect on the ASR engine’s performance.
DeVerb is an anti-reverberation algorithm that detects, analyzes, and reduces room reflection sounds to increase clarity and intelligibility for online calls, conferencing, and Voice Assistance. Sounding closer and more intimate improves communication and focus, especially in scenarios where everyone may not be able to hover over one device.
For manufacturers, DeVerb improves VoIP clarity when challenged by microphone placement or quality, and enhances ASR accuracy as speech recognition algorithms are disrupted by reverberant sounds.